Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Fish Audio / S1

Fish Audio S1

Full-sized proprietary speech model with 13 languages and parenthesized emotion controls. Scheduled to be replaced behind its API selector at the end of 2026.

deprecatedClosed weightsText-to-speech
Official documentation (opens in a new tab)Reviewed 13 Oct 2026
12 of 22 specification fields collected
Output formatsWAV, PCM, MP3, OpusSee specification notes below
Languages13 listedFull language list in specifications
Input billingSee ratesFish Audio 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
Text, AudioSource for Input modalities (opens in a new tab)

Audio is optional voice-conditioning input, not arbitrary audio understanding.

Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Architecture
Not collected
Languages
View all 13 entries
  • English
  • Chinese
  • Japanese
  • German
  • French
  • Spanish
  • Korean
  • Arabic
  • Russian
  • Dutch
  • Italian
  • Polish
  • Portuguese
Source for Languages (opens in a new tab)
Context caching
Not collected
Output formats
WAV, PCM, MP3, OpusSource for Output formats (opens in a new tab)
Audio sample rates
Default 44,100 Hz for most formats; 48,000 Hz for OpusSource for Audio sample rates (opens in a new tab)
Generation controls
Text chunks 100–300 characters; min chunk 0–100. max_new_tokens defaults to 1,024 audio tokens per chunk. Temperature/top_p 0–1; latency normal/balanced/lowSource for Generation controls (opens in a new tab)

Chunk controls are not total input or output limits. Internal batching is not a public batch API.

Voice cloning
Library voice IDs or reference audio with transcripts; persistent private voice profiles can be created separatelySource for Voice cloning (opens in a new tab)

Recommended recording duration is guidance, not an established hard request limit. Cloning does not prove base-model fine-tuning.

Audio controls
Parenthesized emotion and delivery markersSource for Audio controls (opens in a new tab)
Published price
$15 per 1M UTF-8 input bytesSource for Published price (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
s1
Access
Deprecated model; scheduled retirement December 31, 2026, after which requests route to S2.1 Pro.
Regions
Processing region and residency not established for this access path.
API endpoint URL
https://api.fish.audio/v1/ttsSource for API endpoint URL (opens in a new tab)
Request quotas
Shared account concurrency: 5 below $100 total prepaid; 15 from $100; 50 from $1,000; enterprise customSource for Request quotas (opens in a new tab)

Thresholds measure total prepaid funds, not spend. All keys and ASR share the pool; 429 responses have no Retry-After header. Free-tier fair-use conditions also apply.

Request mode
Raw audio responseSource for Request mode (opens in a new tab)
Required request fields
Send the exact model HTTP header. Text plus optional reference_id or inline reference audio; timestamp and WebSocket payloads follow their own contracts.Source for Required request fields (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 synthesis1$15.001M UTF-8 bytes

Rate conditions

  1. Native input text measured in UTF-8 bytes, not Unicode characters or LLM tokens. Pay as you go without a monthly minimum. S1 pricing applies before its scheduled replacement.
Pricing source (opens in a new tab)

Data & enterprise terms

Fish Audio terms permit Usage Data and Content to improve its models, including third-party components. Public terms do not establish universal zero retention. Free S2.1 has no DPA or TTFA guarantees; confirm production contractual terms separately. Voice inputs require appropriate rights.

Read the service policy (opens in a new tab)
API model ID
s1
Access
Deprecated model; scheduled retirement December 31, 2026, after which requests route to S2.1 Pro.
Regions
Processing region and residency not established for this access path.
API endpoint URL
https://api.fish.audio/v1/tts/stream/with-timestampSource for API endpoint URL (opens in a new tab)
Request quotas
Shared account concurrency: 5 below $100 total prepaid; 15 from $100; 50 from $1,000; enterprise customSource for Request quotas (opens in a new tab)

Thresholds measure total prepaid funds, not spend. All keys and ASR share the pool; 429 responses have no Retry-After header. Free-tier fair-use conditions also apply.

Request mode
SSE audio with word timestampsSource for Request mode (opens in a new tab)
Required request fields
Send the exact model HTTP header. Text plus optional reference_id or inline reference audio; timestamp and WebSocket payloads follow their own contracts.Source for Required request fields (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 synthesis1$15.001M UTF-8 bytes

Rate conditions

  1. Native input text measured in UTF-8 bytes, not Unicode characters or LLM tokens. Pay as you go without a monthly minimum. S1 pricing applies before its scheduled replacement.
Pricing source (opens in a new tab)

Data & enterprise terms

Fish Audio terms permit Usage Data and Content to improve its models, including third-party components. Public terms do not establish universal zero retention. Free S2.1 has no DPA or TTFA guarantees; confirm production contractual terms separately. Voice inputs require appropriate rights.

Read the service policy (opens in a new tab)
API model ID
s1
Access
Deprecated model; scheduled retirement December 31, 2026, after which requests route to S2.1 Pro.
Regions
Processing region and residency not established for this access path.
API endpoint URL
wss://api.fish.audio/v1/tts/liveSource for API endpoint URL (opens in a new tab)
Request quotas
Shared account concurrency: 5 below $100 total prepaid; 15 from $100; 50 from $1,000; enterprise customSource for Request quotas (opens in a new tab)

Thresholds measure total prepaid funds, not spend. All keys and ASR share the pool; 429 responses have no Retry-After header. Free-tier fair-use conditions also apply.

Request mode
Streaming text input and audio outputSource for Request mode (opens in a new tab)
Required request fields
Send the exact model HTTP header. Text plus optional reference_id or inline reference audio; timestamp and WebSocket payloads follow their own contracts.Source for Required request fields (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 synthesis1$15.001M UTF-8 bytes

Rate conditions

  1. Native input text measured in UTF-8 bytes, not Unicode characters or LLM tokens. Pay as you go without a monthly minimum. S1 pricing applies before its scheduled replacement.
Pricing source (opens in a new tab)

Data & enterprise terms

Fish Audio terms permit Usage Data and Content to improve its models, including third-party components. Public terms do not establish universal zero retention. Free S2.1 has no DPA or TTFA guarantees; confirm production contractual terms separately. Voice inputs require appropriate rights.

Read the service policy (opens in a new tab)
API model ID
s1
Access
Deprecated model; scheduled retirement December 31, 2026, after which requests route to S2.1 Pro.
Regions
Processing region and residency not established for this access path.
API endpoint URL
wss://api.fish.audio/v1/tts/live/with-timestampSource for API endpoint URL (opens in a new tab)
Request quotas
Shared account concurrency: 5 below $100 total prepaid; 15 from $100; 50 from $1,000; enterprise customSource for Request quotas (opens in a new tab)

Thresholds measure total prepaid funds, not spend. All keys and ASR share the pool; 429 responses have no Retry-After header. Free-tier fair-use conditions also apply.

Request mode
Streaming text/audio with timestamp eventsSource for Request mode (opens in a new tab)
Required request fields
Send the exact model HTTP header. Text plus optional reference_id or inline reference audio; timestamp and WebSocket payloads follow their own contracts.Source for Required request fields (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 synthesis1$15.001M UTF-8 bytes

Rate conditions

  1. Native input text measured in UTF-8 bytes, not Unicode characters or LLM tokens. Pay as you go without a monthly minimum. S1 pricing applies before its scheduled replacement.
Pricing source (opens in a new tab)

Data & enterprise terms

Fish Audio terms permit Usage Data and Content to improve its models, including third-party components. Public terms do not establish universal zero retention. Free S2.1 has no DPA or TTFA guarantees; confirm production contractual terms separately. Voice inputs require appropriate rights.

Read the service policy (opens in a new tab)
API model ID
fish-audio/s1
Access
Listed by OpenRouter. Upstream availability, account access and routing policy apply; host listing date is not the native model release date.
Regions
Processing region and residency not established for this access path.
API endpoint URL
https://openrouter.ai/api/v1/audio/speechSource for API endpoint URL (opens in a new tab)
Request mode
Text input to raw audio byte stream, with optional voice and input reference audioSource 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 synthesis1$15.001M UTF-8 bytes

Rate conditions

  1. OpenRouter published host rate. Rates are not transferred to other hosts.
Pricing source (opens in a new tab)

Data & enterprise terms

OpenRouter prompt/response logging and improvement use are opt-in; metadata is retained. Upstream provider policies remain separate, so routing through OpenRouter does not itself establish Fish Audio zero retention.

Read the service policy (opens in a new tab)
API model ID
fish-audio/s1
Access
Listed in the public AI Gateway model catalog. Use a supported speech/transcription SDK specification; native HTTP contracts are not presumed identical.
Regions
Processing region and residency not established for this access path.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Speech synthesisSpeech synthesis1$15.001M characters

Rate conditions

  1. Uses the catalog’s dedicated speech_input_character_cost field. Generic input fields are not treated as LLM token prices. Native Fish byte units are not substituted for gateway character units.
Pricing source (opens in a new tab)

Data & enterprise terms

The catalog labels this model zdr=none and no_training=none. No zero-retention or no-training guarantee is inferred; confirm host and upstream terms for the intended workload.

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.

Fish Audio API

s1
Not verified

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

How it works
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

Minimum reusable input
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

Lifetime & refresh
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

How to enable it
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

Usage fields
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

Billing rules
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

Limits & data boundaries
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

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

Fish Audio API

s1
Not verified

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

How it works
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

Minimum reusable input
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

Lifetime & refresh
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

How to enable it
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

Usage fields
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

Billing rules
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

Limits & data boundaries
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

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

Fish Audio API

s1
Not verified

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

How it works
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

Minimum reusable input
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

Lifetime & refresh
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

How to enable it
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

Usage fields
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

Billing rules
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

Limits & data boundaries
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

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

Fish Audio API

s1
Not verified

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

How it works
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

Minimum reusable input
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

Lifetime & refresh
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

How to enable it
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

Usage fields
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

Billing rules
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

Limits & data boundaries
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

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

OpenRouter

fish-audio/s1
Not verified

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

How it works
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

Minimum reusable input
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

Lifetime & refresh
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

How to enable it
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

Usage fields
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

Billing rules
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

Limits & data boundaries
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

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

Vercel AI Gateway

fish-audio/s1
Not verified

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

How it works
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

Minimum reusable input
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

Lifetime & refresh
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

How to enable it
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

Usage fields
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

Billing rules
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed prompt caching.

Limits & data boundaries
Not collected

No model-specific prompt-cache contract or discount established. Voice references and previous-chunk conditioning are not billed 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

The official S1-mini model card explicitly identifies the full S1 4B model as proprietary. The downloadable 0.5B distilled S1-mini is a different release.

Classification evidence (opens in a new tab)

Lifecycle dates

Deprecation announced8 Oct 2026Source (opens in a new tab)
Scheduled retirement; selector then routes to S2.1 Pro31 Dec 2026Source (opens in a new tab)

Sources reviewed