Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Murf AI / Falcon

Murf Falcon 2

Conversational speech generation over HTTP and bidirectional WebSockets, with mixed-language delivery, regional routing and privately licensed on-premise deployment.

availableClosed weightsText-to-speech
Official documentation (opens in a new tab)Reviewed 13 Oct 2026
13 of 23 specification fields collected
Text input limit3,000 characters / requestSee specification notes below
Languages35 listedFull language list in specifications
Input billingSee ratesMurf API
Output billingSee ratesPublished units and conditions below

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
Not collected
Maximum output
Not collected
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Batch processing
Not collected
Fine-tuning
SupportedSource for Fine-tuning (opens in a new tab)

Provider-managed professional custom voice-model creation, supported for Falcon 2 by the Instant vs Professional comparison. Instant clones alone are not fine-tuning evidence.

Knowledge cutoff
Not collected
Parameters
Not collected
Architecture
Not collected
Languages
View all 35 entries
  • as-IN · Assamese - India
  • bn-IN · Bangla - India
  • cs-CZ · Czech - Czech Republic
  • de-DE · German - Germany
  • el-GR · Greek - Greece
  • en-AU · English - Australia
  • en-IN · English - India
  • en-SCOTT · English - Scotland
  • en-UK · English - UK
  • en-US · English - US & Canada
  • es-ES · Spanish - Spain
  • es-MX · Spanish - Mexico
  • fr-CA · French - Canada
  • fr-FR · French - France
  • gu-IN · Gujarati - India
  • hi-IN · Hindi - India
  • hi-LATN · Hinglish - India
  • it-IT · Italian - Italy
  • ja-JP · Japanese - Japan
  • kn-IN · Kannada - India
  • ko-KR · Korean - South Korea
  • ml-IN · Malayalam - India
  • mr-IN · Marathi - India
  • nl-NL · Dutch - Netherlands
  • or-IN · Odia - India
  • pa-IN · Punjabi - India
  • pl-PL · Polish - Poland
  • pt-BR · Portuguese - Brazil
  • sk-SK · Slovak - Slovakia
  • ta-IN · Tamil - India
  • te-IN · Telugu - India
  • tl-PH · Tagalog - Philippines
  • tr-TR · Turkish - Turkey
  • vi-VN · Vietnamese - Vietnam
  • zh-CN · Mandarin - China
Source for Languages (opens in a new tab)

Locales explicitly present in the public model-specific voice table; support varies by voice. Locales and accents are not distinct languages. Truncated locale lists are not expanded by guesswork.

Context caching
Not collected
Maximum prompt characters
3,000 characters / requestSource for Maximum prompt characters (opens in a new tab)

The general TTS API FAQ gives this request limit. A cumulative WebSocket context limit is not separately established; do not treat this as a token window or total session cap.

Audio formats
MP3, FLAC, WAV, ALAW, ULAW, OGG, PCMSource for Audio formats (opens in a new tab)
Audio sample rates
8, 16, 24, 44.1 or 48 kHz; streaming default 24 kHz; mono or stereoSource for Audio sample rates (opens in a new tab)
Generation controls
Voice, supported locale and voice-specific style; rate and pitch −50 to 50; volumeOffset −50 to 50 (default 0); predictive chunking and word timestamps on WebSocketsSource for Generation controls (opens in a new tab)
Voice cloning
Enterprise instant clone from one sample up to 30 seconds and 40 MB, at least 24 kHz. Creation/storage have no extra fee; standard Falcon 2 synthesis or contracted enterprise rates apply. Professional cloning also available.Source for Voice cloning (opens in a new tab)

Instant cloning requires workspace enablement and has no model training wait. Styles are unavailable on instant clones. Clone quotas are contract-specific.

Deployment options
Native HTTP/WebSocket API, 11 regional environments, global router, or licensed private data center/VPC deploymentSource for Deployment options (opens in a new tab)

Cloud regional inventory is documented by the separate data-residency guide.

Voice references
135 unique voice IDs in the reviewed public table; multilingual rows merged by IDSource for Voice references (opens in a new tab)

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

API model ID
falcon-2
Access
HTTP streaming. Submit text and receive audio chunks.
Regions
Nearest available region; routing may cross borders and is not a strict residency commitment.
API endpoint URL
https://global.api.murf.ai/v1/speech/streamSource for API endpoint URL (opens in a new tab)
Concurrent requests
Free/PAYG: 2 active contexts; enterprise custom per regionSource for Concurrent requests (opens in a new tab)

The rate-limit table gives 2 for global; the region guide also describes routing-dependent limits. Use the explicit US-East endpoint for its 5-context allowance.

Maximum prompt characters
3,000 characters / requestSource for Maximum prompt characters (opens in a new tab)

The general TTS API FAQ gives this request limit. A cumulative WebSocket context limit is not separately established; do not treat this as a token window or total session cap.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Speech usageSpeech synthesis1$10.001M characters

Rate conditions

  1. Native pay-as-you-go usage. $10 minimum credit purchase; purchased credits do not expire. Enterprise contracts may differ. Character-based billing is not a text-token rate; free trial credit is a finite allowance.
Pricing source (opens in a new tab)

Data & enterprise terms

Residency applies to Falcon 2 processing when configured for the selected region. Account profiles, usage and billing remain hosted in the US. Geographic confinement does not independently establish zero retention or a no-training contract.

Read the service policy (opens in a new tab)
API model ID
falcon-2
Access
Bidirectional WebSocket: stream text input and receive audio frames; use context_id for turns.
Regions
Nearest available region; routing may cross borders and is not a strict residency commitment.
API endpoint URL
wss://global.api.murf.ai/v1/speech/stream-inputSource for API endpoint URL (opens in a new tab)
Concurrent requests
Free/PAYG: 2 active contexts; enterprise custom per regionSource for Concurrent requests (opens in a new tab)

The rate-limit table gives 2 for global; the region guide also describes routing-dependent limits. Use the explicit US-East endpoint for its 5-context allowance.

Session duration
Connection closes after 3 minutes of inactivity; maximum active session duration not collectedSource for Session duration (opens in a new tab)
Open connection limit
Open sockets: 10 times active-context concurrency. Idle sockets do not consume generation concurrency.Source for Open connection limit (opens in a new tab)
Speech timestamps and alignment
Opt-in add_word_timestamps at the frame top level; connection-wide. Excludes Chinese, Japanese and Korean locales.Source for Speech timestamps and alignment (opens in a new tab)
Request mode
predictive_chunking strict/lenient; min_buffer_size and max_buffer_delay_in_ms control flush timing. end closes a turn; clear discards pending audio for barge-in.Source for Request mode (opens in a new tab)

Chunking controls are documented in the separate advanced-settings source. Context reuse is not discounted prompt caching.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Speech usageSpeech synthesis1$10.001M characters

Rate conditions

  1. Native pay-as-you-go usage. $10 minimum credit purchase; purchased credits do not expire. Enterprise contracts may differ. Character-based billing is not a text-token rate; free trial credit is a finite allowance.
Pricing source (opens in a new tab)

Data & enterprise terms

Residency applies to Falcon 2 processing when configured for the selected region. Account profiles, usage and billing remain hosted in the US. Geographic confinement does not independently establish zero retention or a no-training contract.

Read the service policy (opens in a new tab)
API model ID
falcon-2
Access
HTTP streaming. Submit text and receive audio chunks.
Regions
US East. Enterprise residency can confine text, audio and intermediate processing here; account metadata remains in the US.
API endpoint URL
https://us-east.api.murf.ai/v1/speech/streamSource for API endpoint URL (opens in a new tab)
Concurrent requests
Free/PAYG: 5 active contexts; enterprise custom (advertised up to 10,000)Source for Concurrent requests (opens in a new tab)
Maximum prompt characters
3,000 characters / requestSource for Maximum prompt characters (opens in a new tab)

The general TTS API FAQ gives this request limit. A cumulative WebSocket context limit is not separately established; do not treat this as a token window or total session cap.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Speech usageSpeech synthesis1$10.001M characters

Rate conditions

  1. Native pay-as-you-go usage. $10 minimum credit purchase; purchased credits do not expire. Enterprise contracts may differ. Character-based billing is not a text-token rate; free trial credit is a finite allowance.
Pricing source (opens in a new tab)

Data & enterprise terms

Residency applies to Falcon 2 processing when configured for the selected region. Account profiles, usage and billing remain hosted in the US. Geographic confinement does not independently establish zero retention or a no-training contract.

Read the service policy (opens in a new tab)
API model ID
falcon-2
Access
Bidirectional WebSocket: stream text input and receive audio frames; use context_id for turns.
Regions
US East. Enterprise residency can confine text, audio and intermediate processing here; account metadata remains in the US.
API endpoint URL
wss://us-east.api.murf.ai/v1/speech/stream-inputSource for API endpoint URL (opens in a new tab)
Concurrent requests
Free/PAYG: 5 active contexts; enterprise custom (advertised up to 10,000)Source for Concurrent requests (opens in a new tab)
Session duration
Connection closes after 3 minutes of inactivity; maximum active session duration not collectedSource for Session duration (opens in a new tab)
Open connection limit
Open sockets: 10 times active-context concurrency. Idle sockets do not consume generation concurrency.Source for Open connection limit (opens in a new tab)
Speech timestamps and alignment
Opt-in add_word_timestamps at the frame top level; connection-wide. Excludes Chinese, Japanese and Korean locales.Source for Speech timestamps and alignment (opens in a new tab)
Request mode
predictive_chunking strict/lenient; min_buffer_size and max_buffer_delay_in_ms control flush timing. end closes a turn; clear discards pending audio for barge-in.Source for Request mode (opens in a new tab)

Chunking controls are documented in the separate advanced-settings source. Context reuse is not discounted prompt caching.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Speech usageSpeech synthesis1$10.001M characters

Rate conditions

  1. Native pay-as-you-go usage. $10 minimum credit purchase; purchased credits do not expire. Enterprise contracts may differ. Character-based billing is not a text-token rate; free trial credit is a finite allowance.
Pricing source (opens in a new tab)

Data & enterprise terms

Residency applies to Falcon 2 processing when configured for the selected region. Account profiles, usage and billing remain hosted in the US. Geographic confinement does not independently establish zero retention or a no-training contract.

Read the service policy (opens in a new tab)
API model ID
falcon-2
Access
HTTP streaming. Submit text and receive audio chunks.
Regions
US West. Enterprise residency can confine text, audio and intermediate processing here; account metadata remains in the US.
API endpoint URL
https://us-west.api.murf.ai/v1/speech/streamSource for API endpoint URL (opens in a new tab)
Concurrent requests
Free/PAYG: 2 active contexts; enterprise custom per regionSource for Concurrent requests (opens in a new tab)
Maximum prompt characters
3,000 characters / requestSource for Maximum prompt characters (opens in a new tab)

The general TTS API FAQ gives this request limit. A cumulative WebSocket context limit is not separately established; do not treat this as a token window or total session cap.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Speech usageSpeech synthesis1$10.001M characters

Rate conditions

  1. Native pay-as-you-go usage. $10 minimum credit purchase; purchased credits do not expire. Enterprise contracts may differ. Character-based billing is not a text-token rate; free trial credit is a finite allowance.
Pricing source (opens in a new tab)

Data & enterprise terms

Residency applies to Falcon 2 processing when configured for the selected region. Account profiles, usage and billing remain hosted in the US. Geographic confinement does not independently establish zero retention or a no-training contract.

Read the service policy (opens in a new tab)
API model ID
falcon-2
Access
Bidirectional WebSocket: stream text input and receive audio frames; use context_id for turns.
Regions
US West. Enterprise residency can confine text, audio and intermediate processing here; account metadata remains in the US.
API endpoint URL
wss://us-west.api.murf.ai/v1/speech/stream-inputSource for API endpoint URL (opens in a new tab)
Concurrent requests
Free/PAYG: 2 active contexts; enterprise custom per regionSource for Concurrent requests (opens in a new tab)
Session duration
Connection closes after 3 minutes of inactivity; maximum active session duration not collectedSource for Session duration (opens in a new tab)
Open connection limit
Open sockets: 10 times active-context concurrency. Idle sockets do not consume generation concurrency.Source for Open connection limit (opens in a new tab)
Speech timestamps and alignment
Opt-in add_word_timestamps at the frame top level; connection-wide. Excludes Chinese, Japanese and Korean locales.Source for Speech timestamps and alignment (opens in a new tab)
Request mode
predictive_chunking strict/lenient; min_buffer_size and max_buffer_delay_in_ms control flush timing. end closes a turn; clear discards pending audio for barge-in.Source for Request mode (opens in a new tab)

Chunking controls are documented in the separate advanced-settings source. Context reuse is not discounted prompt caching.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Speech usageSpeech synthesis1$10.001M characters

Rate conditions

  1. Native pay-as-you-go usage. $10 minimum credit purchase; purchased credits do not expire. Enterprise contracts may differ. Character-based billing is not a text-token rate; free trial credit is a finite allowance.
Pricing source (opens in a new tab)

Data & enterprise terms

Residency applies to Falcon 2 processing when configured for the selected region. Account profiles, usage and billing remain hosted in the US. Geographic confinement does not independently establish zero retention or a no-training contract.

Read the service policy (opens in a new tab)
API model ID
falcon-2
Access
HTTP streaming. Submit text and receive audio chunks.
Regions
India. Enterprise residency can confine text, audio and intermediate processing here; account metadata remains in the US.
API endpoint URL
https://in.api.murf.ai/v1/speech/streamSource for API endpoint URL (opens in a new tab)
Concurrent requests
Free/PAYG: 2 active contexts; enterprise custom per regionSource for Concurrent requests (opens in a new tab)
Maximum prompt characters
3,000 characters / requestSource for Maximum prompt characters (opens in a new tab)

The general TTS API FAQ gives this request limit. A cumulative WebSocket context limit is not separately established; do not treat this as a token window or total session cap.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Speech usageSpeech synthesis1$10.001M characters

Rate conditions

  1. Native pay-as-you-go usage. $10 minimum credit purchase; purchased credits do not expire. Enterprise contracts may differ. Character-based billing is not a text-token rate; free trial credit is a finite allowance.
Pricing source (opens in a new tab)

Data & enterprise terms

Residency applies to Falcon 2 processing when configured for the selected region. Account profiles, usage and billing remain hosted in the US. Geographic confinement does not independently establish zero retention or a no-training contract.

Read the service policy (opens in a new tab)
API model ID
falcon-2
Access
Bidirectional WebSocket: stream text input and receive audio frames; use context_id for turns.
Regions
India. Enterprise residency can confine text, audio and intermediate processing here; account metadata remains in the US.
API endpoint URL
wss://in.api.murf.ai/v1/speech/stream-inputSource for API endpoint URL (opens in a new tab)
Concurrent requests
Free/PAYG: 2 active contexts; enterprise custom per regionSource for Concurrent requests (opens in a new tab)
Session duration
Connection closes after 3 minutes of inactivity; maximum active session duration not collectedSource for Session duration (opens in a new tab)
Open connection limit
Open sockets: 10 times active-context concurrency. Idle sockets do not consume generation concurrency.Source for Open connection limit (opens in a new tab)
Speech timestamps and alignment
Opt-in add_word_timestamps at the frame top level; connection-wide. Excludes Chinese, Japanese and Korean locales.Source for Speech timestamps and alignment (opens in a new tab)
Request mode
predictive_chunking strict/lenient; min_buffer_size and max_buffer_delay_in_ms control flush timing. end closes a turn; clear discards pending audio for barge-in.Source for Request mode (opens in a new tab)

Chunking controls are documented in the separate advanced-settings source. Context reuse is not discounted prompt caching.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Speech usageSpeech synthesis1$10.001M characters

Rate conditions

  1. Native pay-as-you-go usage. $10 minimum credit purchase; purchased credits do not expire. Enterprise contracts may differ. Character-based billing is not a text-token rate; free trial credit is a finite allowance.
Pricing source (opens in a new tab)

Data & enterprise terms

Residency applies to Falcon 2 processing when configured for the selected region. Account profiles, usage and billing remain hosted in the US. Geographic confinement does not independently establish zero retention or a no-training contract.

Read the service policy (opens in a new tab)
API model ID
falcon-2
Access
HTTP streaming. Submit text and receive audio chunks.
Regions
Canada. Enterprise residency can confine text, audio and intermediate processing here; account metadata remains in the US.
API endpoint URL
https://ca.api.murf.ai/v1/speech/streamSource for API endpoint URL (opens in a new tab)
Concurrent requests
Free/PAYG: 2 active contexts; enterprise custom per regionSource for Concurrent requests (opens in a new tab)
Maximum prompt characters
3,000 characters / requestSource for Maximum prompt characters (opens in a new tab)

The general TTS API FAQ gives this request limit. A cumulative WebSocket context limit is not separately established; do not treat this as a token window or total session cap.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Speech usageSpeech synthesis1$10.001M characters

Rate conditions

  1. Native pay-as-you-go usage. $10 minimum credit purchase; purchased credits do not expire. Enterprise contracts may differ. Character-based billing is not a text-token rate; free trial credit is a finite allowance.
Pricing source (opens in a new tab)

Data & enterprise terms

Residency applies to Falcon 2 processing when configured for the selected region. Account profiles, usage and billing remain hosted in the US. Geographic confinement does not independently establish zero retention or a no-training contract.

Read the service policy (opens in a new tab)
API model ID
falcon-2
Access
Bidirectional WebSocket: stream text input and receive audio frames; use context_id for turns.
Regions
Canada. Enterprise residency can confine text, audio and intermediate processing here; account metadata remains in the US.
API endpoint URL
wss://ca.api.murf.ai/v1/speech/stream-inputSource for API endpoint URL (opens in a new tab)
Concurrent requests
Free/PAYG: 2 active contexts; enterprise custom per regionSource for Concurrent requests (opens in a new tab)
Session duration
Connection closes after 3 minutes of inactivity; maximum active session duration not collectedSource for Session duration (opens in a new tab)
Open connection limit
Open sockets: 10 times active-context concurrency. Idle sockets do not consume generation concurrency.Source for Open connection limit (opens in a new tab)
Speech timestamps and alignment
Opt-in add_word_timestamps at the frame top level; connection-wide. Excludes Chinese, Japanese and Korean locales.Source for Speech timestamps and alignment (opens in a new tab)
Request mode
predictive_chunking strict/lenient; min_buffer_size and max_buffer_delay_in_ms control flush timing. end closes a turn; clear discards pending audio for barge-in.Source for Request mode (opens in a new tab)

Chunking controls are documented in the separate advanced-settings source. Context reuse is not discounted prompt caching.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Speech usageSpeech synthesis1$10.001M characters

Rate conditions

  1. Native pay-as-you-go usage. $10 minimum credit purchase; purchased credits do not expire. Enterprise contracts may differ. Character-based billing is not a text-token rate; free trial credit is a finite allowance.
Pricing source (opens in a new tab)

Data & enterprise terms

Residency applies to Falcon 2 processing when configured for the selected region. Account profiles, usage and billing remain hosted in the US. Geographic confinement does not independently establish zero retention or a no-training contract.

Read the service policy (opens in a new tab)
API model ID
falcon-2
Access
HTTP streaming. Submit text and receive audio chunks.
Regions
South Korea. Enterprise residency can confine text, audio and intermediate processing here; account metadata remains in the US.
API endpoint URL
https://kr.api.murf.ai/v1/speech/streamSource for API endpoint URL (opens in a new tab)
Concurrent requests
Free/PAYG: 2 active contexts; enterprise custom per regionSource for Concurrent requests (opens in a new tab)
Maximum prompt characters
3,000 characters / requestSource for Maximum prompt characters (opens in a new tab)

The general TTS API FAQ gives this request limit. A cumulative WebSocket context limit is not separately established; do not treat this as a token window or total session cap.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Speech usageSpeech synthesis1$10.001M characters

Rate conditions

  1. Native pay-as-you-go usage. $10 minimum credit purchase; purchased credits do not expire. Enterprise contracts may differ. Character-based billing is not a text-token rate; free trial credit is a finite allowance.
Pricing source (opens in a new tab)

Data & enterprise terms

Residency applies to Falcon 2 processing when configured for the selected region. Account profiles, usage and billing remain hosted in the US. Geographic confinement does not independently establish zero retention or a no-training contract.

Read the service policy (opens in a new tab)
API model ID
falcon-2
Access
Bidirectional WebSocket: stream text input and receive audio frames; use context_id for turns.
Regions
South Korea. Enterprise residency can confine text, audio and intermediate processing here; account metadata remains in the US.
API endpoint URL
wss://kr.api.murf.ai/v1/speech/stream-inputSource for API endpoint URL (opens in a new tab)
Concurrent requests
Free/PAYG: 2 active contexts; enterprise custom per regionSource for Concurrent requests (opens in a new tab)
Session duration
Connection closes after 3 minutes of inactivity; maximum active session duration not collectedSource for Session duration (opens in a new tab)
Open connection limit
Open sockets: 10 times active-context concurrency. Idle sockets do not consume generation concurrency.Source for Open connection limit (opens in a new tab)
Speech timestamps and alignment
Opt-in add_word_timestamps at the frame top level; connection-wide. Excludes Chinese, Japanese and Korean locales.Source for Speech timestamps and alignment (opens in a new tab)
Request mode
predictive_chunking strict/lenient; min_buffer_size and max_buffer_delay_in_ms control flush timing. end closes a turn; clear discards pending audio for barge-in.Source for Request mode (opens in a new tab)

Chunking controls are documented in the separate advanced-settings source. Context reuse is not discounted prompt caching.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Speech usageSpeech synthesis1$10.001M characters

Rate conditions

  1. Native pay-as-you-go usage. $10 minimum credit purchase; purchased credits do not expire. Enterprise contracts may differ. Character-based billing is not a text-token rate; free trial credit is a finite allowance.
Pricing source (opens in a new tab)

Data & enterprise terms

Residency applies to Falcon 2 processing when configured for the selected region. Account profiles, usage and billing remain hosted in the US. Geographic confinement does not independently establish zero retention or a no-training contract.

Read the service policy (opens in a new tab)
API model ID
falcon-2
Access
HTTP streaming. Submit text and receive audio chunks.
Regions
UAE. Enterprise residency can confine text, audio and intermediate processing here; account metadata remains in the US.
API endpoint URL
https://me.api.murf.ai/v1/speech/streamSource for API endpoint URL (opens in a new tab)
Concurrent requests
Free/PAYG: 2 active contexts; enterprise custom per regionSource for Concurrent requests (opens in a new tab)
Maximum prompt characters
3,000 characters / requestSource for Maximum prompt characters (opens in a new tab)

The general TTS API FAQ gives this request limit. A cumulative WebSocket context limit is not separately established; do not treat this as a token window or total session cap.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Speech usageSpeech synthesis1$10.001M characters

Rate conditions

  1. Native pay-as-you-go usage. $10 minimum credit purchase; purchased credits do not expire. Enterprise contracts may differ. Character-based billing is not a text-token rate; free trial credit is a finite allowance.
Pricing source (opens in a new tab)

Data & enterprise terms

Residency applies to Falcon 2 processing when configured for the selected region. Account profiles, usage and billing remain hosted in the US. Geographic confinement does not independently establish zero retention or a no-training contract.

Read the service policy (opens in a new tab)
API model ID
falcon-2
Access
Bidirectional WebSocket: stream text input and receive audio frames; use context_id for turns.
Regions
UAE. Enterprise residency can confine text, audio and intermediate processing here; account metadata remains in the US.
API endpoint URL
wss://me.api.murf.ai/v1/speech/stream-inputSource for API endpoint URL (opens in a new tab)
Concurrent requests
Free/PAYG: 2 active contexts; enterprise custom per regionSource for Concurrent requests (opens in a new tab)
Session duration
Connection closes after 3 minutes of inactivity; maximum active session duration not collectedSource for Session duration (opens in a new tab)
Open connection limit
Open sockets: 10 times active-context concurrency. Idle sockets do not consume generation concurrency.Source for Open connection limit (opens in a new tab)
Speech timestamps and alignment
Opt-in add_word_timestamps at the frame top level; connection-wide. Excludes Chinese, Japanese and Korean locales.Source for Speech timestamps and alignment (opens in a new tab)
Request mode
predictive_chunking strict/lenient; min_buffer_size and max_buffer_delay_in_ms control flush timing. end closes a turn; clear discards pending audio for barge-in.Source for Request mode (opens in a new tab)

Chunking controls are documented in the separate advanced-settings source. Context reuse is not discounted prompt caching.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Speech usageSpeech synthesis1$10.001M characters

Rate conditions

  1. Native pay-as-you-go usage. $10 minimum credit purchase; purchased credits do not expire. Enterprise contracts may differ. Character-based billing is not a text-token rate; free trial credit is a finite allowance.
Pricing source (opens in a new tab)

Data & enterprise terms

Residency applies to Falcon 2 processing when configured for the selected region. Account profiles, usage and billing remain hosted in the US. Geographic confinement does not independently establish zero retention or a no-training contract.

Read the service policy (opens in a new tab)
API model ID
falcon-2
Access
HTTP streaming. Submit text and receive audio chunks.
Regions
Japan. Enterprise residency can confine text, audio and intermediate processing here; account metadata remains in the US.
API endpoint URL
https://jp.api.murf.ai/v1/speech/streamSource for API endpoint URL (opens in a new tab)
Concurrent requests
Free/PAYG: 2 active contexts; enterprise custom per regionSource for Concurrent requests (opens in a new tab)
Maximum prompt characters
3,000 characters / requestSource for Maximum prompt characters (opens in a new tab)

The general TTS API FAQ gives this request limit. A cumulative WebSocket context limit is not separately established; do not treat this as a token window or total session cap.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Speech usageSpeech synthesis1$10.001M characters

Rate conditions

  1. Native pay-as-you-go usage. $10 minimum credit purchase; purchased credits do not expire. Enterprise contracts may differ. Character-based billing is not a text-token rate; free trial credit is a finite allowance.
Pricing source (opens in a new tab)

Data & enterprise terms

Residency applies to Falcon 2 processing when configured for the selected region. Account profiles, usage and billing remain hosted in the US. Geographic confinement does not independently establish zero retention or a no-training contract.

Read the service policy (opens in a new tab)
API model ID
falcon-2
Access
Bidirectional WebSocket: stream text input and receive audio frames; use context_id for turns.
Regions
Japan. Enterprise residency can confine text, audio and intermediate processing here; account metadata remains in the US.
API endpoint URL
wss://jp.api.murf.ai/v1/speech/stream-inputSource for API endpoint URL (opens in a new tab)
Concurrent requests
Free/PAYG: 2 active contexts; enterprise custom per regionSource for Concurrent requests (opens in a new tab)
Session duration
Connection closes after 3 minutes of inactivity; maximum active session duration not collectedSource for Session duration (opens in a new tab)
Open connection limit
Open sockets: 10 times active-context concurrency. Idle sockets do not consume generation concurrency.Source for Open connection limit (opens in a new tab)
Speech timestamps and alignment
Opt-in add_word_timestamps at the frame top level; connection-wide. Excludes Chinese, Japanese and Korean locales.Source for Speech timestamps and alignment (opens in a new tab)
Request mode
predictive_chunking strict/lenient; min_buffer_size and max_buffer_delay_in_ms control flush timing. end closes a turn; clear discards pending audio for barge-in.Source for Request mode (opens in a new tab)

Chunking controls are documented in the separate advanced-settings source. Context reuse is not discounted prompt caching.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Speech usageSpeech synthesis1$10.001M characters

Rate conditions

  1. Native pay-as-you-go usage. $10 minimum credit purchase; purchased credits do not expire. Enterprise contracts may differ. Character-based billing is not a text-token rate; free trial credit is a finite allowance.
Pricing source (opens in a new tab)

Data & enterprise terms

Residency applies to Falcon 2 processing when configured for the selected region. Account profiles, usage and billing remain hosted in the US. Geographic confinement does not independently establish zero retention or a no-training contract.

Read the service policy (opens in a new tab)
API model ID
falcon-2
Access
HTTP streaming. Submit text and receive audio chunks.
Regions
Australia. Enterprise residency can confine text, audio and intermediate processing here; account metadata remains in the US.
API endpoint URL
https://au.api.murf.ai/v1/speech/streamSource for API endpoint URL (opens in a new tab)
Concurrent requests
Free/PAYG: 2 active contexts; enterprise custom per regionSource for Concurrent requests (opens in a new tab)
Maximum prompt characters
3,000 characters / requestSource for Maximum prompt characters (opens in a new tab)

The general TTS API FAQ gives this request limit. A cumulative WebSocket context limit is not separately established; do not treat this as a token window or total session cap.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Speech usageSpeech synthesis1$10.001M characters

Rate conditions

  1. Native pay-as-you-go usage. $10 minimum credit purchase; purchased credits do not expire. Enterprise contracts may differ. Character-based billing is not a text-token rate; free trial credit is a finite allowance.
Pricing source (opens in a new tab)

Data & enterprise terms

Residency applies to Falcon 2 processing when configured for the selected region. Account profiles, usage and billing remain hosted in the US. Geographic confinement does not independently establish zero retention or a no-training contract.

Read the service policy (opens in a new tab)
API model ID
falcon-2
Access
Bidirectional WebSocket: stream text input and receive audio frames; use context_id for turns.
Regions
Australia. Enterprise residency can confine text, audio and intermediate processing here; account metadata remains in the US.
API endpoint URL
wss://au.api.murf.ai/v1/speech/stream-inputSource for API endpoint URL (opens in a new tab)
Concurrent requests
Free/PAYG: 2 active contexts; enterprise custom per regionSource for Concurrent requests (opens in a new tab)
Session duration
Connection closes after 3 minutes of inactivity; maximum active session duration not collectedSource for Session duration (opens in a new tab)
Open connection limit
Open sockets: 10 times active-context concurrency. Idle sockets do not consume generation concurrency.Source for Open connection limit (opens in a new tab)
Speech timestamps and alignment
Opt-in add_word_timestamps at the frame top level; connection-wide. Excludes Chinese, Japanese and Korean locales.Source for Speech timestamps and alignment (opens in a new tab)
Request mode
predictive_chunking strict/lenient; min_buffer_size and max_buffer_delay_in_ms control flush timing. end closes a turn; clear discards pending audio for barge-in.Source for Request mode (opens in a new tab)

Chunking controls are documented in the separate advanced-settings source. Context reuse is not discounted prompt caching.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Speech usageSpeech synthesis1$10.001M characters

Rate conditions

  1. Native pay-as-you-go usage. $10 minimum credit purchase; purchased credits do not expire. Enterprise contracts may differ. Character-based billing is not a text-token rate; free trial credit is a finite allowance.
Pricing source (opens in a new tab)

Data & enterprise terms

Residency applies to Falcon 2 processing when configured for the selected region. Account profiles, usage and billing remain hosted in the US. Geographic confinement does not independently establish zero retention or a no-training contract.

Read the service policy (opens in a new tab)
API model ID
falcon-2
Access
HTTP streaming. Submit text and receive audio chunks.
Regions
EU Central. Enterprise residency can confine text, audio and intermediate processing here; account metadata remains in the US.
API endpoint URL
https://eu-central.api.murf.ai/v1/speech/streamSource for API endpoint URL (opens in a new tab)
Concurrent requests
Free/PAYG: 2 active contexts; enterprise custom per regionSource for Concurrent requests (opens in a new tab)
Maximum prompt characters
3,000 characters / requestSource for Maximum prompt characters (opens in a new tab)

The general TTS API FAQ gives this request limit. A cumulative WebSocket context limit is not separately established; do not treat this as a token window or total session cap.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Speech usageSpeech synthesis1$10.001M characters

Rate conditions

  1. Native pay-as-you-go usage. $10 minimum credit purchase; purchased credits do not expire. Enterprise contracts may differ. Character-based billing is not a text-token rate; free trial credit is a finite allowance.
Pricing source (opens in a new tab)

Data & enterprise terms

Residency applies to Falcon 2 processing when configured for the selected region. Account profiles, usage and billing remain hosted in the US. Geographic confinement does not independently establish zero retention or a no-training contract.

Read the service policy (opens in a new tab)
API model ID
falcon-2
Access
Bidirectional WebSocket: stream text input and receive audio frames; use context_id for turns.
Regions
EU Central. Enterprise residency can confine text, audio and intermediate processing here; account metadata remains in the US.
API endpoint URL
wss://eu-central.api.murf.ai/v1/speech/stream-inputSource for API endpoint URL (opens in a new tab)
Concurrent requests
Free/PAYG: 2 active contexts; enterprise custom per regionSource for Concurrent requests (opens in a new tab)
Session duration
Connection closes after 3 minutes of inactivity; maximum active session duration not collectedSource for Session duration (opens in a new tab)
Open connection limit
Open sockets: 10 times active-context concurrency. Idle sockets do not consume generation concurrency.Source for Open connection limit (opens in a new tab)
Speech timestamps and alignment
Opt-in add_word_timestamps at the frame top level; connection-wide. Excludes Chinese, Japanese and Korean locales.Source for Speech timestamps and alignment (opens in a new tab)
Request mode
predictive_chunking strict/lenient; min_buffer_size and max_buffer_delay_in_ms control flush timing. end closes a turn; clear discards pending audio for barge-in.Source for Request mode (opens in a new tab)

Chunking controls are documented in the separate advanced-settings source. Context reuse is not discounted prompt caching.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Speech usageSpeech synthesis1$10.001M characters

Rate conditions

  1. Native pay-as-you-go usage. $10 minimum credit purchase; purchased credits do not expire. Enterprise contracts may differ. Character-based billing is not a text-token rate; free trial credit is a finite allowance.
Pricing source (opens in a new tab)

Data & enterprise terms

Residency applies to Falcon 2 processing when configured for the selected region. Account profiles, usage and billing remain hosted in the US. Geographic confinement does not independently establish zero retention or a no-training contract.

Read the service policy (opens in a new tab)
API model ID
falcon-2
Access
HTTP streaming. Submit text and receive audio chunks.
Regions
UK. Enterprise residency can confine text, audio and intermediate processing here; account metadata remains in the US.
API endpoint URL
https://uk.api.murf.ai/v1/speech/streamSource for API endpoint URL (opens in a new tab)
Concurrent requests
Free/PAYG: 2 active contexts; enterprise custom per regionSource for Concurrent requests (opens in a new tab)
Maximum prompt characters
3,000 characters / requestSource for Maximum prompt characters (opens in a new tab)

The general TTS API FAQ gives this request limit. A cumulative WebSocket context limit is not separately established; do not treat this as a token window or total session cap.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Speech usageSpeech synthesis1$10.001M characters

Rate conditions

  1. Native pay-as-you-go usage. $10 minimum credit purchase; purchased credits do not expire. Enterprise contracts may differ. Character-based billing is not a text-token rate; free trial credit is a finite allowance.
Pricing source (opens in a new tab)

Data & enterprise terms

Residency applies to Falcon 2 processing when configured for the selected region. Account profiles, usage and billing remain hosted in the US. Geographic confinement does not independently establish zero retention or a no-training contract.

Read the service policy (opens in a new tab)
API model ID
falcon-2
Access
Bidirectional WebSocket: stream text input and receive audio frames; use context_id for turns.
Regions
UK. Enterprise residency can confine text, audio and intermediate processing here; account metadata remains in the US.
API endpoint URL
wss://uk.api.murf.ai/v1/speech/stream-inputSource for API endpoint URL (opens in a new tab)
Concurrent requests
Free/PAYG: 2 active contexts; enterprise custom per regionSource for Concurrent requests (opens in a new tab)
Session duration
Connection closes after 3 minutes of inactivity; maximum active session duration not collectedSource for Session duration (opens in a new tab)
Open connection limit
Open sockets: 10 times active-context concurrency. Idle sockets do not consume generation concurrency.Source for Open connection limit (opens in a new tab)
Speech timestamps and alignment
Opt-in add_word_timestamps at the frame top level; connection-wide. Excludes Chinese, Japanese and Korean locales.Source for Speech timestamps and alignment (opens in a new tab)
Request mode
predictive_chunking strict/lenient; min_buffer_size and max_buffer_delay_in_ms control flush timing. end closes a turn; clear discards pending audio for barge-in.Source for Request mode (opens in a new tab)

Chunking controls are documented in the separate advanced-settings source. Context reuse is not discounted prompt caching.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Speech usageSpeech synthesis1$10.001M characters

Rate conditions

  1. Native pay-as-you-go usage. $10 minimum credit purchase; purchased credits do not expire. Enterprise contracts may differ. Character-based billing is not a text-token rate; free trial credit is a finite allowance.
Pricing source (opens in a new tab)

Data & enterprise terms

Residency applies to Falcon 2 processing when configured for the selected region. Account profiles, usage and billing remain hosted in the US. Geographic confinement does not independently establish zero retention or a no-training contract.

Read the service policy (opens in a new tab)
API model ID
falcon-2
Access
HTTP streaming. Submit text and receive audio chunks.
Regions
São Paulo, Brazil. Enterprise residency can confine text, audio and intermediate processing here; account metadata remains in the US.
API endpoint URL
https://sa-east.api.murf.ai/v1/speech/streamSource for API endpoint URL (opens in a new tab)
Concurrent requests
Free/PAYG: 2 active contexts; enterprise custom per regionSource for Concurrent requests (opens in a new tab)
Maximum prompt characters
3,000 characters / requestSource for Maximum prompt characters (opens in a new tab)

The general TTS API FAQ gives this request limit. A cumulative WebSocket context limit is not separately established; do not treat this as a token window or total session cap.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Speech usageSpeech synthesis1$10.001M characters

Rate conditions

  1. Native pay-as-you-go usage. $10 minimum credit purchase; purchased credits do not expire. Enterprise contracts may differ. Character-based billing is not a text-token rate; free trial credit is a finite allowance.
Pricing source (opens in a new tab)

Data & enterprise terms

Residency applies to Falcon 2 processing when configured for the selected region. Account profiles, usage and billing remain hosted in the US. Geographic confinement does not independently establish zero retention or a no-training contract.

Read the service policy (opens in a new tab)
API model ID
falcon-2
Access
Bidirectional WebSocket: stream text input and receive audio frames; use context_id for turns.
Regions
São Paulo, Brazil. Enterprise residency can confine text, audio and intermediate processing here; account metadata remains in the US.
API endpoint URL
wss://sa-east.api.murf.ai/v1/speech/stream-inputSource for API endpoint URL (opens in a new tab)
Concurrent requests
Free/PAYG: 2 active contexts; enterprise custom per regionSource for Concurrent requests (opens in a new tab)
Session duration
Connection closes after 3 minutes of inactivity; maximum active session duration not collectedSource for Session duration (opens in a new tab)
Open connection limit
Open sockets: 10 times active-context concurrency. Idle sockets do not consume generation concurrency.Source for Open connection limit (opens in a new tab)
Speech timestamps and alignment
Opt-in add_word_timestamps at the frame top level; connection-wide. Excludes Chinese, Japanese and Korean locales.Source for Speech timestamps and alignment (opens in a new tab)
Request mode
predictive_chunking strict/lenient; min_buffer_size and max_buffer_delay_in_ms control flush timing. end closes a turn; clear discards pending audio for barge-in.Source for Request mode (opens in a new tab)

Chunking controls are documented in the separate advanced-settings source. Context reuse is not discounted prompt caching.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Speech usageSpeech synthesis1$10.001M characters

Rate conditions

  1. Native pay-as-you-go usage. $10 minimum credit purchase; purchased credits do not expire. Enterprise contracts may differ. Character-based billing is not a text-token rate; free trial credit is a finite allowance.
Pricing source (opens in a new tab)

Data & enterprise terms

Residency applies to Falcon 2 processing when configured for the selected region. Account profiles, usage and billing remain hosted in the US. Geographic confinement does not independently establish zero retention or a no-training contract.

Read the service policy (opens in a new tab)
API model ID
falcon-2
Access
Default API hostname documented by Stream Speech reference. Use an explicit region endpoint if residency is required.
Regions
No endpoint-specific residency commitment collected.
API endpoint URL
https://api.murf.ai/v1/speech/streamSource for API endpoint URL (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Speech usageSpeech synthesis1$10.001M characters

Rate conditions

  1. Native pay-as-you-go usage. $10 minimum credit purchase; purchased credits do not expire. Enterprise contracts may differ. Character-based billing is not a text-token rate; free trial credit is a finite allowance.
Pricing source (opens in a new tab)

Data & enterprise terms

General privacy policy retains personal/account data while the account remains open or needed for services, with stated exceptions after closure. Clone recordings have separate consent, storage and quality-assurance terms. No universal no-training or zero-retention promise is inferred.

Read the service policy (opens in a new tab)
API model ID
Not collected

No separate pinned model selector is documented for this service or historical access.

Access
Enterprise activation and private container assets required. Customer data center or customer-owned VPC on AWS, Azure, GCP, OCI, or arranged infrastructure.
Regions
Customer-selected private deployment.
Hardware requirements
TTS minimum: NVIDIA GPU ≥8 GB VRAM, 4 vCPU, 16 GB RAM, 50 GB SSD, CUDA 12.4+. Recommended: 16 GB+ GPU, 8+ vCPU, 32 GB RAM, 100 GB SSD.Source for Hardware requirements (opens in a new tab)
Local licensing requirements
Separate LLA minimum: 1–2 vCPU, 1.5 GiB RAM and 5 GB disk; Linux x86_64, Docker. Licensing requires outbound HTTPS.Source for Local licensing requirements (opens in a new tab)

Endpoint pricing has not been collected. Check the provider for applicable rates.

Data & enterprise terms

Audio synthesis runs within the customer network. Local License Agent still requires outbound access to Murf licensing and designated API endpoints. Limited-connectivity operation is documented; a permanently air-gapped license or exact telemetry payload is not established.

Read the service policy (opens in a new tab)

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

Murf API

falcon-2
Not verified

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How it works
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Minimum reusable input
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Lifetime & refresh
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How to enable it
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Usage fields
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Billing rules
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Limits & data boundaries
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Murf API

falcon-2
Not verified

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How it works
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Minimum reusable input
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Lifetime & refresh
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How to enable it
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Usage fields
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Billing rules
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Limits & data boundaries
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Murf API

falcon-2
Not verified

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How it works
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Minimum reusable input
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Lifetime & refresh
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How to enable it
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Usage fields
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Billing rules
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Limits & data boundaries
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Murf API

falcon-2
Not verified

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How it works
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Minimum reusable input
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Lifetime & refresh
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How to enable it
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Usage fields
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Billing rules
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Limits & data boundaries
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Murf API

falcon-2
Not verified

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How it works
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Minimum reusable input
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Lifetime & refresh
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How to enable it
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Usage fields
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Billing rules
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Limits & data boundaries
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Murf API

falcon-2
Not verified

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How it works
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Minimum reusable input
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Lifetime & refresh
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How to enable it
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Usage fields
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Billing rules
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Limits & data boundaries
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Murf API

falcon-2
Not verified

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How it works
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Minimum reusable input
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Lifetime & refresh
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How to enable it
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Usage fields
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Billing rules
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Limits & data boundaries
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Murf API

falcon-2
Not verified

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How it works
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Minimum reusable input
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Lifetime & refresh
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How to enable it
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Usage fields
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Billing rules
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Limits & data boundaries
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Murf API

falcon-2
Not verified

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How it works
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Minimum reusable input
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Lifetime & refresh
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How to enable it
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Usage fields
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Billing rules
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Limits & data boundaries
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Murf API

falcon-2
Not verified

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How it works
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Minimum reusable input
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Lifetime & refresh
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How to enable it
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Usage fields
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Billing rules
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Limits & data boundaries
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Murf API

falcon-2
Not verified

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How it works
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Minimum reusable input
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Lifetime & refresh
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How to enable it
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Usage fields
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Billing rules
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Limits & data boundaries
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Murf API

falcon-2
Not verified

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How it works
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Minimum reusable input
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Lifetime & refresh
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How to enable it
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Usage fields
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Billing rules
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Limits & data boundaries
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Murf API

falcon-2
Not verified

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How it works
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Minimum reusable input
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Lifetime & refresh
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How to enable it
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Usage fields
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Billing rules
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Limits & data boundaries
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Murf API

falcon-2
Not verified

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How it works
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Minimum reusable input
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Lifetime & refresh
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How to enable it
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Usage fields
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Billing rules
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Limits & data boundaries
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Murf API

falcon-2
Not verified

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How it works
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Minimum reusable input
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Lifetime & refresh
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How to enable it
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Usage fields
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Billing rules
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Limits & data boundaries
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Murf API

falcon-2
Not verified

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How it works
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Minimum reusable input
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Lifetime & refresh
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How to enable it
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Usage fields
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Billing rules
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Limits & data boundaries
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Murf API

falcon-2
Not verified

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How it works
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Minimum reusable input
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Lifetime & refresh
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How to enable it
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Usage fields
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Billing rules
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Limits & data boundaries
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Murf API

falcon-2
Not verified

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How it works
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Minimum reusable input
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Lifetime & refresh
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How to enable it
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Usage fields
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Billing rules
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Limits & data boundaries
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Murf API

falcon-2
Not verified

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How it works
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Minimum reusable input
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Lifetime & refresh
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How to enable it
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Usage fields
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Billing rules
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Limits & data boundaries
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Murf API

falcon-2
Not verified

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How it works
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Minimum reusable input
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Lifetime & refresh
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How to enable it
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Usage fields
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Billing rules
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Limits & data boundaries
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Murf API

falcon-2
Not verified

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How it works
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Minimum reusable input
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Lifetime & refresh
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How to enable it
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Usage fields
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Billing rules
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Limits & data boundaries
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Murf API

falcon-2
Not verified

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How it works
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Minimum reusable input
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Lifetime & refresh
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How to enable it
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Usage fields
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Billing rules
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Limits & data boundaries
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Murf API

falcon-2
Not verified

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How it works
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Minimum reusable input
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Lifetime & refresh
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How to enable it
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Usage fields
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Billing rules
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Limits & data boundaries
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Murf API

falcon-2
Not verified

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How it works
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Minimum reusable input
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Lifetime & refresh
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How to enable it
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Usage fields
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Billing rules
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Limits & data boundaries
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Murf API

falcon-2
Not verified

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How it works
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Minimum reusable input
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Lifetime & refresh
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How to enable it
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Usage fields
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Billing rules
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Limits & data boundaries
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Licensed on-premise

Not verified

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How it works
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Minimum reusable input
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Lifetime & refresh
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

How to enable it
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Usage fields
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Billing rules
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

Limits & data boundaries
Not collected

No reviewed model-specific discounted prompt-cache contract. WebSocket context IDs and persistent voice profiles are not evidence of prompt caching.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Voice choices

135 voices

Choose a voice within Murf Falcon 2. These are API voice identifiers, not additional model releases. Source links document each voice.

Published voice catalog
Voice / API IDLanguage & accentDelivery
AliciaAliciaen-US (English - US & Canada)
English - US & Canada
Published styles: Conversation. Exact name-based ID as listed in the Falcon 2 voice table; do not manufacture a locale-prefixed selector.Voice source (opens in a new tab)
AlinaAlinaen-US (English - US & Canada)
English - US & Canada
Published styles: Conversation. Exact name-based ID as listed in the Falcon 2 voice table; do not manufacture a locale-prefixed selector.Voice source (opens in a new tab)
AmaraAmaraen-US (English - US & Canada)
English - US & Canada
Published styles: Conversational. Exact name-based ID as listed in the Falcon 2 voice table; do not manufacture a locale-prefixed selector.Voice source (opens in a new tab)
AngelaAngelaen-US (English - US & Canada)
English - US & Canada
Published styles: Promo. Exact name-based ID as listed in the Falcon 2 voice table; do not manufacture a locale-prefixed selector.Voice source (opens in a new tab)
ArianaArianaen-US (English - US & Canada)
English - US & Canada
Published styles: Conversation. Exact name-based ID as listed in the Falcon 2 voice table; do not manufacture a locale-prefixed selector.Voice source (opens in a new tab)
CalebCaleben-US (English - US & Canada)
English - US & Canada
Published styles: Conversation. Exact name-based ID as listed in the Falcon 2 voice table; do not manufacture a locale-prefixed selector.Voice source (opens in a new tab)
CharlesCharlesen-US (English - US & Canada)
English - US & Canada
Published styles: Conversation. Exact name-based ID as listed in the Falcon 2 voice table; do not manufacture a locale-prefixed selector.Voice source (opens in a new tab)
CooperCooperen-US (English - US & Canada)
English - US & Canada
Published styles: Conversation. Exact name-based ID as listed in the Falcon 2 voice table; do not manufacture a locale-prefixed selector.Voice source (opens in a new tab)

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Murf reserves proprietary rights to its technology and restricts copying, distribution and reverse engineering. Its speech models are supplied through managed services or privately licensed deployment assets, not an open-weight grant. Service records do not establish independently identified foundation checkpoints.

Classification evidence (opens in a new tab)

Lifecycle dates

Release documented16 Jun 2026Source (opens in a new tab)
WebSocket word timestamps added9 Oct 2026Source (opens in a new tab)
Streaming volumeOffset added13 Oct 2026Source (opens in a new tab)

Sources reviewed