Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Soniox / Soniox TTS

TTS v2

Multilingual speech generation with streamed text input, expressive audio tags and voice cloning.

availableClosed weightsText-to-speech
Official documentation (opens in a new tab)Reviewed 13 Oct 2026
12 of 23 specification fields collected
Output formats9 optionsSee specification notes below
Languages60 listedFull language list in specifications
Input billingSee ratesSoniox 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
Not collected
Knowledge cutoff
Not collected
Parameters
Not collected
Architecture
Not collected
Languages
View all 60 entries
  • Afrikaans (af)
  • Albanian (sq)
  • Arabic (ar)
  • Azerbaijani (az)
  • Basque (eu)
  • Belarusian (be)
  • Bengali (bn)
  • Bosnian (bs)
  • Bulgarian (bg)
  • Catalan (ca)
  • Chinese (zh)
  • Croatian (hr)
  • Czech (cs)
  • Danish (da)
  • Dutch (nl)
  • English (en)
  • Estonian (et)
  • Finnish (fi)
  • French (fr)
  • Galician (gl)
  • German (de)
  • Greek (el)
  • Gujarati (gu)
  • Hebrew (he)
  • Hindi (hi)
  • Hungarian (hu)
  • Indonesian (id)
  • Italian (it)
  • Japanese (ja)
  • Kannada (kn)
  • Kazakh (kk)
  • Korean (ko)
  • Latvian (lv)
  • Lithuanian (lt)
  • Macedonian (mk)
  • Malay (ms)
  • Malayalam (ml)
  • Marathi (mr)
  • Norwegian (no)
  • Persian (fa)
  • Polish (pl)
  • Portuguese (pt)
  • Punjabi (pa)
  • Romanian (ro)
  • Russian (ru)
  • Serbian (sr)
  • Slovak (sk)
  • Slovenian (sl)
  • Spanish (es)
  • Swahili (sw)
  • Swedish (sv)
  • Tagalog (tl)
  • Tamil (ta)
  • Telugu (te)
  • Thai (th)
  • Turkish (tr)
  • Ukrainian (uk)
  • Urdu (ur)
  • Vietnamese (vi)
  • Welsh (cy)
Source for Languages (opens in a new tab)

The current table enumerates 60 languages. Marketing says 60+; the older v1 OpenAPI example lists 62, which is not treated as the current v2 inventory.

Context caching
Not collected
Output duration
Up to two minutes of generated audio per WebSocket streamSource for Output duration (opens in a new tab)

Fixed cap; output is truncated with an error. No identical REST duration cap is inferred.

Output formats
PCM float32 little-endian, PCM signed16 little-endian, μ-law, A-law, WAV, FLAC, MP3, Opus, AACSource for Output formats (opens in a new tab)
Audio controls
English-written audio tags for emotion, vocal delivery and reactionsSource for Audio controls (opens in a new tab)
Generation controls
Speaking speed 0.7–1.3; optional silence reduction when supportedSource for Generation controls (opens in a new tab)

Transport schema and model capability flags determine accepted controls.

Voice cloning
Reference audio up to two minutes and 35 MB; default 20 voices per organizationSource for Voice cloning (opens in a new tab)

Preparing an existing voice for a new model does not create a new base-model release.

Published price
Input text $4/M tokens; generated audio $21.50/M audio tokensSource for Published price (opens in a new tab)
Usage metering
About $0.70/hour of generated speech under provider usage assumptions; actual token usage is billedSource for Usage metering (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
tts-rt-v2
Access
Available to API customers with appropriate project key, balance and region access. Voice compatibility is model-specific.
Regions
United States
API endpoint URL
wss://tts-rt.soniox.com/tts-websocketSource for API endpoint URL (opens in a new tab)
Equivalent API aliases
tts-rt-v1Source for Equivalent API aliases (opens in a new tab)

v1 requests route to v2 after August 31, 2026.

Output formats
PCM float32 little-endian, PCM signed16 little-endian, μ-law, A-law, WAV, FLAC, MP3, Opus, AACSource for Output formats (opens in a new tab)
Generation controls
Speaking speed 0.7–1.3; silence reduction requires supports_silence_reductionSource for Generation controls (opens in a new tab)
Regional processing
US, EU, Japan and India model deployment; residency covers content, not system dataSource for Regional processing (opens in a new tab)
Output duration
Up to two minutes of generated audio per WebSocket streamSource for Output duration (opens in a new tab)

Fixed cap; output is truncated with an error. No identical REST duration cap is inferred.

Request quotas
Default 100 requests/minute and three concurrent streams across connections; fixed maximum five streams per connectionSource for Request quotas (opens in a new tab)
Request mode
Stream text chunks and receive audio; use keepalive within the 40-second idle windowSource for Request mode (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 APIInput text1$4.001M text tokens
Speech APIOutput audio1$21.501M audio tokens

Rate conditions

  1. Published modality-specific token rate. Hourly equivalents on the pricing page are illustrative, not separate flat charges. Text context and translated output contribute to usage. Regional enterprise agreements may differ; these are public list rates. No generic text-question estimate.
Pricing source (opens in a new tab)

Data & enterprise terms

Provider states submitted content is not used to train or improve models. Real-time audio/transcript content is not retained; async files and transcripts are stored, deletable by the customer and automatically removed after 30 days. Operational usage metadata is retained. Regional residency excludes account, billing and other system data.

Read the service policy (opens in a new tab)
API model ID
tts-rt-v2
Access
Available to API customers with appropriate project key, balance and region access. Voice compatibility is model-specific.
Regions
United States
API endpoint URL
https://tts-rt.soniox.com/ttsSource for API endpoint URL (opens in a new tab)
Equivalent API aliases
tts-rt-v1Source for Equivalent API aliases (opens in a new tab)

v1 requests route to v2 after August 31, 2026.

Output formats
PCM float32 little-endian, PCM signed16 little-endian, μ-law, A-law, WAV, FLAC, MP3, Opus, AACSource for Output formats (opens in a new tab)
Generation controls
Speaking speed 0.7–1.3; silence reduction requires supports_silence_reductionSource for Generation controls (opens in a new tab)
Regional processing
US, EU, Japan and India model deployment; residency covers content, not system dataSource for Regional processing (opens in a new tab)
Request mode
One text body to audio response; WebSocket multi-stream controls do not applySource for Request mode (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 APIInput text1$4.001M text tokens
Speech APIOutput audio1$21.501M audio tokens

Rate conditions

  1. Published modality-specific token rate. Hourly equivalents on the pricing page are illustrative, not separate flat charges. Text context and translated output contribute to usage. Regional enterprise agreements may differ; these are public list rates. No generic text-question estimate.
Pricing source (opens in a new tab)

Data & enterprise terms

Provider states submitted content is not used to train or improve models. Real-time audio/transcript content is not retained; async files and transcripts are stored, deletable by the customer and automatically removed after 30 days. Operational usage metadata is retained. Regional residency excludes account, billing and other system data.

Read the service policy (opens in a new tab)
API model ID
tts-rt-v2
Access
Available to API customers with appropriate project key, balance and region access. Voice compatibility is model-specific.
Regions
European Union
API endpoint URL
wss://tts-rt.eu.soniox.com/tts-websocketSource for API endpoint URL (opens in a new tab)
Equivalent API aliases
tts-rt-v1Source for Equivalent API aliases (opens in a new tab)

v1 requests route to v2 after August 31, 2026.

Output formats
PCM float32 little-endian, PCM signed16 little-endian, μ-law, A-law, WAV, FLAC, MP3, Opus, AACSource for Output formats (opens in a new tab)
Generation controls
Speaking speed 0.7–1.3; silence reduction requires supports_silence_reductionSource for Generation controls (opens in a new tab)
Regional processing
US, EU, Japan and India model deployment; residency covers content, not system dataSource for Regional processing (opens in a new tab)
Output duration
Up to two minutes of generated audio per WebSocket streamSource for Output duration (opens in a new tab)

Fixed cap; output is truncated with an error. No identical REST duration cap is inferred.

Request quotas
Default 100 requests/minute and three concurrent streams across connections; fixed maximum five streams per connectionSource for Request quotas (opens in a new tab)
Request mode
Stream text chunks and receive audio; use keepalive within the 40-second idle windowSource for Request mode (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 APIInput text1$4.001M text tokens
Speech APIOutput audio1$21.501M audio tokens

Rate conditions

  1. Published modality-specific token rate. Hourly equivalents on the pricing page are illustrative, not separate flat charges. Text context and translated output contribute to usage. Regional enterprise agreements may differ; these are public list rates. No generic text-question estimate.
Pricing source (opens in a new tab)

Data & enterprise terms

Provider states submitted content is not used to train or improve models. Real-time audio/transcript content is not retained; async files and transcripts are stored, deletable by the customer and automatically removed after 30 days. Operational usage metadata is retained. Regional residency excludes account, billing and other system data.

Read the service policy (opens in a new tab)
API model ID
tts-rt-v2
Access
Available to API customers with appropriate project key, balance and region access. Voice compatibility is model-specific.
Regions
European Union
API endpoint URL
https://tts-rt.eu.soniox.com/ttsSource for API endpoint URL (opens in a new tab)
Equivalent API aliases
tts-rt-v1Source for Equivalent API aliases (opens in a new tab)

v1 requests route to v2 after August 31, 2026.

Output formats
PCM float32 little-endian, PCM signed16 little-endian, μ-law, A-law, WAV, FLAC, MP3, Opus, AACSource for Output formats (opens in a new tab)
Generation controls
Speaking speed 0.7–1.3; silence reduction requires supports_silence_reductionSource for Generation controls (opens in a new tab)
Regional processing
US, EU, Japan and India model deployment; residency covers content, not system dataSource for Regional processing (opens in a new tab)
Request mode
One text body to audio response; WebSocket multi-stream controls do not applySource for Request mode (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 APIInput text1$4.001M text tokens
Speech APIOutput audio1$21.501M audio tokens

Rate conditions

  1. Published modality-specific token rate. Hourly equivalents on the pricing page are illustrative, not separate flat charges. Text context and translated output contribute to usage. Regional enterprise agreements may differ; these are public list rates. No generic text-question estimate.
Pricing source (opens in a new tab)

Data & enterprise terms

Provider states submitted content is not used to train or improve models. Real-time audio/transcript content is not retained; async files and transcripts are stored, deletable by the customer and automatically removed after 30 days. Operational usage metadata is retained. Regional residency excludes account, billing and other system data.

Read the service policy (opens in a new tab)
API model ID
tts-rt-v2
Access
Available to API customers with appropriate project key, balance and region access. Voice compatibility is model-specific.
Regions
Japan
API endpoint URL
wss://tts-rt.jp.soniox.com/tts-websocketSource for API endpoint URL (opens in a new tab)
Equivalent API aliases
tts-rt-v1Source for Equivalent API aliases (opens in a new tab)

v1 requests route to v2 after August 31, 2026.

Output formats
PCM float32 little-endian, PCM signed16 little-endian, μ-law, A-law, WAV, FLAC, MP3, Opus, AACSource for Output formats (opens in a new tab)
Generation controls
Speaking speed 0.7–1.3; silence reduction requires supports_silence_reductionSource for Generation controls (opens in a new tab)
Regional processing
US, EU, Japan and India model deployment; residency covers content, not system dataSource for Regional processing (opens in a new tab)
Output duration
Up to two minutes of generated audio per WebSocket streamSource for Output duration (opens in a new tab)

Fixed cap; output is truncated with an error. No identical REST duration cap is inferred.

Request quotas
Default 100 requests/minute and three concurrent streams across connections; fixed maximum five streams per connectionSource for Request quotas (opens in a new tab)
Request mode
Stream text chunks and receive audio; use keepalive within the 40-second idle windowSource for Request mode (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 APIInput text1$4.001M text tokens
Speech APIOutput audio1$21.501M audio tokens

Rate conditions

  1. Published modality-specific token rate. Hourly equivalents on the pricing page are illustrative, not separate flat charges. Text context and translated output contribute to usage. Regional enterprise agreements may differ; these are public list rates. No generic text-question estimate.
Pricing source (opens in a new tab)

Data & enterprise terms

Provider states submitted content is not used to train or improve models. Real-time audio/transcript content is not retained; async files and transcripts are stored, deletable by the customer and automatically removed after 30 days. Operational usage metadata is retained. Regional residency excludes account, billing and other system data.

Read the service policy (opens in a new tab)
API model ID
tts-rt-v2
Access
Available to API customers with appropriate project key, balance and region access. Voice compatibility is model-specific.
Regions
Japan
API endpoint URL
https://tts-rt.jp.soniox.com/ttsSource for API endpoint URL (opens in a new tab)
Equivalent API aliases
tts-rt-v1Source for Equivalent API aliases (opens in a new tab)

v1 requests route to v2 after August 31, 2026.

Output formats
PCM float32 little-endian, PCM signed16 little-endian, μ-law, A-law, WAV, FLAC, MP3, Opus, AACSource for Output formats (opens in a new tab)
Generation controls
Speaking speed 0.7–1.3; silence reduction requires supports_silence_reductionSource for Generation controls (opens in a new tab)
Regional processing
US, EU, Japan and India model deployment; residency covers content, not system dataSource for Regional processing (opens in a new tab)
Request mode
One text body to audio response; WebSocket multi-stream controls do not applySource for Request mode (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 APIInput text1$4.001M text tokens
Speech APIOutput audio1$21.501M audio tokens

Rate conditions

  1. Published modality-specific token rate. Hourly equivalents on the pricing page are illustrative, not separate flat charges. Text context and translated output contribute to usage. Regional enterprise agreements may differ; these are public list rates. No generic text-question estimate.
Pricing source (opens in a new tab)

Data & enterprise terms

Provider states submitted content is not used to train or improve models. Real-time audio/transcript content is not retained; async files and transcripts are stored, deletable by the customer and automatically removed after 30 days. Operational usage metadata is retained. Regional residency excludes account, billing and other system data.

Read the service policy (opens in a new tab)
API model ID
tts-rt-v2
Access
Available to API customers with appropriate project key, balance and region access. Voice compatibility is model-specific.
Regions
India
API endpoint URL
wss://tts-rt.in.soniox.com/tts-websocketSource for API endpoint URL (opens in a new tab)
Equivalent API aliases
tts-rt-v1Source for Equivalent API aliases (opens in a new tab)

v1 requests route to v2 after August 31, 2026.

Output formats
PCM float32 little-endian, PCM signed16 little-endian, μ-law, A-law, WAV, FLAC, MP3, Opus, AACSource for Output formats (opens in a new tab)
Generation controls
Speaking speed 0.7–1.3; silence reduction requires supports_silence_reductionSource for Generation controls (opens in a new tab)
Regional processing
US, EU, Japan and India model deployment; residency covers content, not system dataSource for Regional processing (opens in a new tab)
Output duration
Up to two minutes of generated audio per WebSocket streamSource for Output duration (opens in a new tab)

Fixed cap; output is truncated with an error. No identical REST duration cap is inferred.

Request quotas
Default 100 requests/minute and three concurrent streams across connections; fixed maximum five streams per connectionSource for Request quotas (opens in a new tab)
Request mode
Stream text chunks and receive audio; use keepalive within the 40-second idle windowSource for Request mode (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 APIInput text1$4.001M text tokens
Speech APIOutput audio1$21.501M audio tokens

Rate conditions

  1. Published modality-specific token rate. Hourly equivalents on the pricing page are illustrative, not separate flat charges. Text context and translated output contribute to usage. Regional enterprise agreements may differ; these are public list rates. No generic text-question estimate.
Pricing source (opens in a new tab)

Data & enterprise terms

Provider states submitted content is not used to train or improve models. Real-time audio/transcript content is not retained; async files and transcripts are stored, deletable by the customer and automatically removed after 30 days. Operational usage metadata is retained. Regional residency excludes account, billing and other system data.

Read the service policy (opens in a new tab)
API model ID
tts-rt-v2
Access
Available to API customers with appropriate project key, balance and region access. Voice compatibility is model-specific.
Regions
India
API endpoint URL
https://tts-rt.in.soniox.com/ttsSource for API endpoint URL (opens in a new tab)
Equivalent API aliases
tts-rt-v1Source for Equivalent API aliases (opens in a new tab)

v1 requests route to v2 after August 31, 2026.

Output formats
PCM float32 little-endian, PCM signed16 little-endian, μ-law, A-law, WAV, FLAC, MP3, Opus, AACSource for Output formats (opens in a new tab)
Generation controls
Speaking speed 0.7–1.3; silence reduction requires supports_silence_reductionSource for Generation controls (opens in a new tab)
Regional processing
US, EU, Japan and India model deployment; residency covers content, not system dataSource for Regional processing (opens in a new tab)
Request mode
One text body to audio response; WebSocket multi-stream controls do not applySource for Request mode (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 APIInput text1$4.001M text tokens
Speech APIOutput audio1$21.501M audio tokens

Rate conditions

  1. Published modality-specific token rate. Hourly equivalents on the pricing page are illustrative, not separate flat charges. Text context and translated output contribute to usage. Regional enterprise agreements may differ; these are public list rates. No generic text-question estimate.
Pricing source (opens in a new tab)

Data & enterprise terms

Provider states submitted content is not used to train or improve models. Real-time audio/transcript content is not retained; async files and transcripts are stored, deletable by the customer and automatically removed after 30 days. Operational usage metadata is retained. Regional residency excludes account, billing and other system data.

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.

Soniox API

tts-rt-v2
Not verified

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

How it works
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Minimum reusable input
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Lifetime & refresh
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

How to enable it
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Usage fields
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Billing rules
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Limits & data boundaries
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

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

Soniox API

tts-rt-v2
Not verified

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

How it works
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Minimum reusable input
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Lifetime & refresh
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

How to enable it
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Usage fields
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Billing rules
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Limits & data boundaries
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

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

Soniox API

tts-rt-v2
Not verified

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

How it works
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Minimum reusable input
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Lifetime & refresh
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

How to enable it
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Usage fields
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Billing rules
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Limits & data boundaries
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

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

Soniox API

tts-rt-v2
Not verified

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

How it works
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Minimum reusable input
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Lifetime & refresh
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

How to enable it
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Usage fields
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Billing rules
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Limits & data boundaries
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

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

Soniox API

tts-rt-v2
Not verified

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

How it works
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Minimum reusable input
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Lifetime & refresh
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

How to enable it
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Usage fields
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Billing rules
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Limits & data boundaries
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

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

Soniox API

tts-rt-v2
Not verified

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

How it works
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Minimum reusable input
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Lifetime & refresh
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

How to enable it
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Usage fields
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Billing rules
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Limits & data boundaries
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

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

Soniox API

tts-rt-v2
Not verified

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

How it works
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Minimum reusable input
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Lifetime & refresh
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

How to enable it
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Usage fields
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Billing rules
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Limits & data boundaries
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

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

Soniox API

tts-rt-v2
Not verified

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

How it works
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Minimum reusable input
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Lifetime & refresh
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

How to enable it
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Usage fields
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Billing rules
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

Limits & data boundaries
Not collected

No model-specific prompt-cache mechanism or discount collected. Structured context, voice preparation and temporary request keys do not establish prompt caching.

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

Voice choices

1 voices

Choose a voice within TTS v2. These are API voice identifiers, not additional model releases. Source links document each voice.

Published voice catalog
Voice / API IDLanguage & accentDelivery
DanielDanielAll supported model languagesCurrent documentation example. This is not the full 200+ built-in voice inventory.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

The provider identifies its hosted models as Soniox intellectual property, grants limited service access and prohibits extraction/reverse engineering. Native release documentation and historical reports establish these model identities; no public weight license is inferred from SDK availability.

Classification evidence (opens in a new tab)

Lifecycle dates

General availability11 Aug 2026Source (opens in a new tab)

Sources reviewed