Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Speechify / Simba

Simba 3.0

Streaming-native speech model serving six languages across seven locales under a single API model ID.

Speech & voice
availableClosed weightsText-to-speech
Official documentation (opens in a new tab)Reviewed 13 Oct 2026
13 of 23 specification fields collected
Text input limit2,000 spoken characters in speech; 20,000 characters including markup in streamSee specification notes below
Languages7 listedFull language list in specifications
Input billingSee ratesSpeechifyAI 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
Input modalities
TextSource for Input modalities (opens in a new tab)
Output modalities
AudioSource for Output modalities (opens in a new tab)
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Streaming
SupportedSource for Streaming (opens in a new tab)

Native audio streaming; HTTP, SSE speech marks and streaming text-input WebSocket are distinct transports.

Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
2026-05-09Source for Release date (opens in a new tab)
Parameters
Not collected
Architecture
Streaming-native speech synthesis; full architecture and parameter count not establishedSource for Architecture (opens in a new tab)
Languages
English (en-*), German (de-DE), Spanish (es-ES), Spanish (es-MX), French (fr-FR), Italian (it-IT), Portuguese (pt-BR)Source for Languages (opens in a new tab)

Seven locale entries represent six languages; Spanish has Spain and Mexico locales.

Context caching
Not collected
Maximum prompt characters
2,000 spoken characters in speech; 20,000 characters including markup in streamSource for Maximum prompt characters (opens in a new tab)

The non-streaming speech request permits up to 20,000 raw characters including SSML, provided spoken text stays within 2,000 Unicode code points.

Output formats
WAV, MP3, OGG, AAC, PCM, μ-lawSource for Output formats (opens in a new tab)

WAV is restricted to non-streamed speech. Codec/sample-rate support varies by endpoint.

Audio controls
SSML pauses, speaking rate and pronunciation; pitch, volume, emphasis and emotion styles are accepted but not appliedSource for Audio controls (opens in a new tab)
Voice cloning
Zero-shot personal voices on paid plans; verified speaker consent and geographic availability applySource for Voice cloning (opens in a new tab)
Audio sample rates
24 kHz model-page sample rate; output encoding supports endpoint-specific 8–48 kHz choicesSource for Audio sample rates (opens in a new tab)

Requested output encoding is not proof of native generation at every output sample rate.

Published price
Starter $10, Pro $8, Scale $6 per 1M spoken characters; monthly subscription additionalSource for Published price (opens in a new tab)
Usage metering
Free: 500K characters/month, then pause. Paid monthly fees: Starter $10, Pro $99, Scale $499Source 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.

SpeechifyAI API

Provider source (opens in a new tab)
API model ID
simba-3.0
Access
Documented API model. Workspace entitlement, voice/language compatibility, balance and plan limits apply.
Regions
Deployment region and residency commitments require service-specific confirmation.
API endpoint URL
https://api.speechify.ai/v1/audio/speechSource for API endpoint URL (opens in a new tab)
Streaming
Not supportedSource for Streaming (opens in a new tab)
Maximum prompt characters
2,000 spoken Unicode code points; at most 20,000 raw characters including markupSource for Maximum prompt characters (opens in a new tab)
Output formats
WAV, MP3, OGG, AAC, PCM, μ-lawSource for Output formats (opens in a new tab)
Request mode
JSON containing Base64 audio and speech marksSource 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 synthesisSpeech synthesis · Starter1$10.001M spoken characters
SubscriptionPlan fee · Starter1$10.00month
Speech synthesisSpeech synthesis · Pro2$8.001M spoken characters
SubscriptionPlan fee · Pro2$99.00month
Speech synthesisSpeech synthesis · Scale3$6.001M spoken characters
SubscriptionPlan fee · Scale3$499.00month

Rate conditions

  1. Starter: $10/month subscription includes 1.9M spoken characters. Published rate draws down the included dollar balance and then purchased top-ups. Monthly allocation expires; purchased top-ups do not. Billable text excludes SSML markup and leading/trailing whitespace; interior spaces count. API subscription only, not the Reader app. No per-question or per-token conversion.
  2. Pro: $99/month subscription includes 13.5M spoken characters. Published rate draws down the included dollar balance and then purchased top-ups. Monthly allocation expires; purchased top-ups do not. Billable text excludes SSML markup and leading/trailing whitespace; interior spaces count. API subscription only, not the Reader app. No per-question or per-token conversion.
  3. Scale: $499/month subscription includes 78M spoken characters. Published rate draws down the included dollar balance and then purchased top-ups. Monthly allocation expires; purchased top-ups do not. Billable text excludes SSML markup and leading/trailing whitespace; interior spaces count. API subscription only, not the Reader app. No per-question or per-token conversion.
Pricing source (opens in a new tab)

Data & enterprise terms

API-specific supplemental terms reserve model IP and require rights to voice inputs. Cloning requires verified speaker consent; the consent recording is retained with the voice. No blanket zero-retention or no-training claim is inferred.

Read the service policy (opens in a new tab)

SpeechifyAI API

Provider source (opens in a new tab)
API model ID
simba-3.0
Access
Documented API model. Workspace entitlement, voice/language compatibility, balance and plan limits apply.
Regions
Deployment region and residency commitments require service-specific confirmation.
API endpoint URL
https://api.speechify.ai/v1/audio/streamSource for API endpoint URL (opens in a new tab)
Streaming
SupportedSource for Streaming (opens in a new tab)
Maximum prompt characters
20,000 characters including SSML markupSource for Maximum prompt characters (opens in a new tab)
Output formats
MP3, OGG, AAC, PCM, μ-lawSource for Output formats (opens in a new tab)
Request mode
Raw audio byte streamSource 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 synthesisSpeech synthesis · Starter1$10.001M spoken characters
SubscriptionPlan fee · Starter1$10.00month
Speech synthesisSpeech synthesis · Pro2$8.001M spoken characters
SubscriptionPlan fee · Pro2$99.00month
Speech synthesisSpeech synthesis · Scale3$6.001M spoken characters
SubscriptionPlan fee · Scale3$499.00month

Rate conditions

  1. Starter: $10/month subscription includes 1.9M spoken characters. Published rate draws down the included dollar balance and then purchased top-ups. Monthly allocation expires; purchased top-ups do not. Billable text excludes SSML markup and leading/trailing whitespace; interior spaces count. API subscription only, not the Reader app. No per-question or per-token conversion.
  2. Pro: $99/month subscription includes 13.5M spoken characters. Published rate draws down the included dollar balance and then purchased top-ups. Monthly allocation expires; purchased top-ups do not. Billable text excludes SSML markup and leading/trailing whitespace; interior spaces count. API subscription only, not the Reader app. No per-question or per-token conversion.
  3. Scale: $499/month subscription includes 78M spoken characters. Published rate draws down the included dollar balance and then purchased top-ups. Monthly allocation expires; purchased top-ups do not. Billable text excludes SSML markup and leading/trailing whitespace; interior spaces count. API subscription only, not the Reader app. No per-question or per-token conversion.
Pricing source (opens in a new tab)

Data & enterprise terms

API-specific supplemental terms reserve model IP and require rights to voice inputs. Cloning requires verified speaker consent; the consent recording is retained with the voice. No blanket zero-retention or no-training claim is inferred.

Read the service policy (opens in a new tab)

SpeechifyAI API

Provider source (opens in a new tab)
API model ID
simba-3.0
Access
Documented API model. Workspace entitlement, voice/language compatibility, balance and plan limits apply.
Regions
Deployment region and residency commitments require service-specific confirmation.
API endpoint URL
https://api.speechify.ai/v1/audio/stream/with-timestampsSource for API endpoint URL (opens in a new tab)
Streaming
SupportedSource for Streaming (opens in a new tab)
Maximum prompt characters
20,000 characters including SSML markupSource for Maximum prompt characters (opens in a new tab)
Output formats
MP3, OGG, AAC, PCM, μ-lawSource for Output formats (opens in a new tab)
Request mode
Server-Sent Events with Base64 audio and absolute word timestampsSource 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 synthesisSpeech synthesis · Starter1$10.001M spoken characters
SubscriptionPlan fee · Starter1$10.00month
Speech synthesisSpeech synthesis · Pro2$8.001M spoken characters
SubscriptionPlan fee · Pro2$99.00month
Speech synthesisSpeech synthesis · Scale3$6.001M spoken characters
SubscriptionPlan fee · Scale3$499.00month

Rate conditions

  1. Starter: $10/month subscription includes 1.9M spoken characters. Published rate draws down the included dollar balance and then purchased top-ups. Monthly allocation expires; purchased top-ups do not. Billable text excludes SSML markup and leading/trailing whitespace; interior spaces count. API subscription only, not the Reader app. No per-question or per-token conversion.
  2. Pro: $99/month subscription includes 13.5M spoken characters. Published rate draws down the included dollar balance and then purchased top-ups. Monthly allocation expires; purchased top-ups do not. Billable text excludes SSML markup and leading/trailing whitespace; interior spaces count. API subscription only, not the Reader app. No per-question or per-token conversion.
  3. Scale: $499/month subscription includes 78M spoken characters. Published rate draws down the included dollar balance and then purchased top-ups. Monthly allocation expires; purchased top-ups do not. Billable text excludes SSML markup and leading/trailing whitespace; interior spaces count. API subscription only, not the Reader app. No per-question or per-token conversion.
Pricing source (opens in a new tab)

Data & enterprise terms

API-specific supplemental terms reserve model IP and require rights to voice inputs. Cloning requires verified speaker consent; the consent recording is retained with the voice. No blanket zero-retention or no-training claim is inferred.

Read the service policy (opens in a new tab)

SpeechifyAI API

Provider source (opens in a new tab)
API model ID
simba-3.0
Access
Documented API model. Workspace entitlement, voice/language compatibility, balance and plan limits apply. Connect server-side with a Bearer header; credentials and text do not belong in the URL.
Regions
Deployment region and residency commitments require service-specific confirmation.
API endpoint URL
wss://api.speechify.ai/v1/audio/stream/wsSource for API endpoint URL (opens in a new tab)
Streaming
SupportedSource for Streaming (opens in a new tab)
Maximum prompt characters
20,000 characters pending synthesis; text frames at most 20,000 charactersSource for Maximum prompt characters (opens in a new tab)
Session duration
60-second idle limit; stops accepting text after five minutesSource for Session duration (opens in a new tab)
Output formats
MP3, OGG, AAC, PCM, μ-lawSource for Output formats (opens in a new tab)
Audio controls
Plain text only; SSML is read aloud, not interpretedSource for Audio controls (opens in a new tab)
Request mode
input.text / input.flush / input.close; Base64 speech.chunk events with optional word timestampsSource for Request mode (opens in a new tab)
Usage metering
Each segment is one synthesis; a session holds one concurrency slot. Unspoken queued text is not billed; interrupted synthesis is billed in fullSource for Usage metering (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 synthesisSpeech synthesis · Starter1$10.001M spoken characters
SubscriptionPlan fee · Starter1$10.00month
Speech synthesisSpeech synthesis · Pro2$8.001M spoken characters
SubscriptionPlan fee · Pro2$99.00month
Speech synthesisSpeech synthesis · Scale3$6.001M spoken characters
SubscriptionPlan fee · Scale3$499.00month

Rate conditions

  1. Starter: $10/month subscription includes 1.9M spoken characters. Published rate draws down the included dollar balance and then purchased top-ups. Monthly allocation expires; purchased top-ups do not. Billable text excludes SSML markup and leading/trailing whitespace; interior spaces count. API subscription only, not the Reader app. No per-question or per-token conversion.
  2. Pro: $99/month subscription includes 13.5M spoken characters. Published rate draws down the included dollar balance and then purchased top-ups. Monthly allocation expires; purchased top-ups do not. Billable text excludes SSML markup and leading/trailing whitespace; interior spaces count. API subscription only, not the Reader app. No per-question or per-token conversion.
  3. Scale: $499/month subscription includes 78M spoken characters. Published rate draws down the included dollar balance and then purchased top-ups. Monthly allocation expires; purchased top-ups do not. Billable text excludes SSML markup and leading/trailing whitespace; interior spaces count. API subscription only, not the Reader app. No per-question or per-token conversion.
Pricing source (opens in a new tab)

Data & enterprise terms

API-specific supplemental terms reserve model IP and require rights to voice inputs. Cloning requires verified speaker consent; the consent recording is retained with the voice. No blanket zero-retention or no-training claim is inferred.

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.

SpeechifyAI API

simba-3.0
Not verified

No model-specific prompt-cache API, lifetime or discount documented in reviewed sources. Voice conditioning, buffered audio and idempotency replay are not prompt caching.

How it works
Not collected

No model-specific prompt-cache API, lifetime or discount documented in reviewed sources. Voice conditioning, buffered audio and idempotency replay are not prompt caching.

Minimum reusable input
Not collected

No model-specific prompt-cache API, lifetime or discount documented in reviewed sources. Voice conditioning, buffered audio and idempotency replay are not prompt caching.

Lifetime & refresh
Not collected

No model-specific prompt-cache API, lifetime or discount documented in reviewed sources. Voice conditioning, buffered audio and idempotency replay are not prompt caching.

How to enable it
Not collected

No model-specific prompt-cache API, lifetime or discount documented in reviewed sources. Voice conditioning, buffered audio and idempotency replay are not prompt caching.

Usage fields
Not collected

No model-specific prompt-cache API, lifetime or discount documented in reviewed sources. Voice conditioning, buffered audio and idempotency replay are not prompt caching.

Billing rules
Not collected

No model-specific prompt-cache API, lifetime or discount documented in reviewed sources. Voice conditioning, buffered audio and idempotency replay are not prompt caching.

Limits & data boundaries
Not collected

No model-specific prompt-cache API, lifetime or discount documented in reviewed sources. Voice conditioning, buffered audio and idempotency replay are not prompt caching.

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

SpeechifyAI API

simba-3.0
Not verified

No model-specific prompt-cache API, lifetime or discount documented in reviewed sources. Voice conditioning, buffered audio and idempotency replay are not prompt caching.

How it works
Not collected

No model-specific prompt-cache API, lifetime or discount documented in reviewed sources. Voice conditioning, buffered audio and idempotency replay are not prompt caching.

Minimum reusable input
Not collected

No model-specific prompt-cache API, lifetime or discount documented in reviewed sources. Voice conditioning, buffered audio and idempotency replay are not prompt caching.

Lifetime & refresh
Not collected

No model-specific prompt-cache API, lifetime or discount documented in reviewed sources. Voice conditioning, buffered audio and idempotency replay are not prompt caching.

How to enable it
Not collected

No model-specific prompt-cache API, lifetime or discount documented in reviewed sources. Voice conditioning, buffered audio and idempotency replay are not prompt caching.

Usage fields
Not collected

No model-specific prompt-cache API, lifetime or discount documented in reviewed sources. Voice conditioning, buffered audio and idempotency replay are not prompt caching.

Billing rules
Not collected

No model-specific prompt-cache API, lifetime or discount documented in reviewed sources. Voice conditioning, buffered audio and idempotency replay are not prompt caching.

Limits & data boundaries
Not collected

No model-specific prompt-cache API, lifetime or discount documented in reviewed sources. Voice conditioning, buffered audio and idempotency replay are not prompt caching.

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

SpeechifyAI API

simba-3.0
Not verified

No model-specific prompt-cache API, lifetime or discount documented in reviewed sources. Voice conditioning, buffered audio and idempotency replay are not prompt caching.

How it works
Not collected

No model-specific prompt-cache API, lifetime or discount documented in reviewed sources. Voice conditioning, buffered audio and idempotency replay are not prompt caching.

Minimum reusable input
Not collected

No model-specific prompt-cache API, lifetime or discount documented in reviewed sources. Voice conditioning, buffered audio and idempotency replay are not prompt caching.

Lifetime & refresh
Not collected

No model-specific prompt-cache API, lifetime or discount documented in reviewed sources. Voice conditioning, buffered audio and idempotency replay are not prompt caching.

How to enable it
Not collected

No model-specific prompt-cache API, lifetime or discount documented in reviewed sources. Voice conditioning, buffered audio and idempotency replay are not prompt caching.

Usage fields
Not collected

No model-specific prompt-cache API, lifetime or discount documented in reviewed sources. Voice conditioning, buffered audio and idempotency replay are not prompt caching.

Billing rules
Not collected

No model-specific prompt-cache API, lifetime or discount documented in reviewed sources. Voice conditioning, buffered audio and idempotency replay are not prompt caching.

Limits & data boundaries
Not collected

No model-specific prompt-cache API, lifetime or discount documented in reviewed sources. Voice conditioning, buffered audio and idempotency replay are not prompt caching.

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

SpeechifyAI API

simba-3.0
Not verified

No model-specific prompt-cache API, lifetime or discount documented in reviewed sources. Voice conditioning, buffered audio and idempotency replay are not prompt caching.

How it works
Not collected

No model-specific prompt-cache API, lifetime or discount documented in reviewed sources. Voice conditioning, buffered audio and idempotency replay are not prompt caching.

Minimum reusable input
Not collected

No model-specific prompt-cache API, lifetime or discount documented in reviewed sources. Voice conditioning, buffered audio and idempotency replay are not prompt caching.

Lifetime & refresh
Not collected

No model-specific prompt-cache API, lifetime or discount documented in reviewed sources. Voice conditioning, buffered audio and idempotency replay are not prompt caching.

How to enable it
Not collected

No model-specific prompt-cache API, lifetime or discount documented in reviewed sources. Voice conditioning, buffered audio and idempotency replay are not prompt caching.

Usage fields
Not collected

No model-specific prompt-cache API, lifetime or discount documented in reviewed sources. Voice conditioning, buffered audio and idempotency replay are not prompt caching.

Billing rules
Not collected

No model-specific prompt-cache API, lifetime or discount documented in reviewed sources. Voice conditioning, buffered audio and idempotency replay are not prompt caching.

Limits & data boundaries
Not collected

No model-specific prompt-cache API, lifetime or discount documented in reviewed sources. Voice conditioning, buffered audio and idempotency replay are not prompt caching.

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

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

Speechify identifies the underlying voice models as its intellectual property, grants service access rather than a public weight license, and restricts reverse engineering. The named model inventory establishes native Simba releases; voice presets and integrations are not counted as new base models.

Classification evidence (opens in a new tab)

Lifecycle dates

API model introduced9 May 2026Source (opens in a new tab)
Became the default when model is omitted5 Aug 2026Source (opens in a new tab)

Sources reviewed