Fish Audio

Developer of speech synthesis, transcription and voice-design models. The catalog separates proprietary releases from the publicly downloadable Fish Speech, S1-mini and S2 Pro weights.

Six reviewed native model records, with direct API and documented OpenRouter, Vercel AI Gateway and LiveKit access paths. Earlier Fish Speech commercial checkpoints and private releases remain under review.

Closed-weight models

Browse by model typeCapabilities can overlap

Start with the job your model needs to do. Then narrow by capabilities, provider and price.

Select up to 3 models to compare

What does one question cost?

Compare every model with the same request.

Input tokensOutput tokens

Estimate = (input tokens × input price + output tokens × output price) / 1,000,000. Include conversation history in input and billed reasoning in output. Input-only decision models ignore the output setting; enter all billed input for one decision, including its question and criteria. Media, tools and discounts are separate.

6 models

Sort by

Model input and output limits, prices and estimated cost per question at the selected token counts.
Input tokensPublished limit*	Output tokensMaximum per response*	Input pricePer 1M tokens	Cost per question1,000 input + 500 outputEstimated · uncached
Not collected	WAV, PCM, MP3, Opusoutput formats	Usage pricing $15.00 / 1M UTF-8 bytesSpeech synthesis · Fish Audio API$15.00 / 1M UTF-8 bytesSpeech synthesis · OpenRouterRates & conditions ↗	Different billing unitPrice details ↗
Not collected	WAV, PCM, MP3, Opusoutput formats	Usage pricing $15.00 / 1M UTF-8 bytesSpeech synthesis · Fish Audio API$0.00 / 1M UTF-8 bytesSpeech synthesis · free tier · Fish Audio APIRates & conditions ↗	Different billing unitPrice details ↗
Not collected	WAV, PCM, MP3, Opusoutput formats	Usage pricingNot collected	Different billing unitPrice details ↗
Up to 50 MiB; MP3 and Opus files must stay below 25 MiBfile limit	JSON transcript, Optional word-level segmentsoutput formats	Usage pricing $0.36 / audio hourTranscription · Fish Audio API$0.0001 / audio secondTranscription · OpenRouterRates & conditions ↗	Different billing unitPrice details ↗
Up to 60 minutes; clips below about 0.08 seconds are rejectedaudio limit	JSON transcript, Optional word-level segments, Optional speaker turnsoutput formats	Usage pricing $0.36 / audio hourTranscription · Fish Audio API$0.0001 / audio secondTranscription · OpenRouterRates & conditions ↗	Different billing unitPrice details ↗
1–2,000 instruction characters; preview text up to 150 characterstext input	Base64 WAV candidates in JSONoutput formats	Usage pricing $0.01 / successful requestVoice design · Fish Audio APIRates & conditions ↗	Different billing unitPrice details ↗

* Media models show their native limits. A shared context window includes both input and output tokens.

Original currency and billing unit, without currency conversion. Rates are dated snapshots; open the conditions for tiers, promotions and endpoint restrictions.How to read the data

Catalog coverage

Closed-weight model variants and explicitly identified closed-source managed model components across language, code, image, video, audio and other documented modalities. Global provider and historical-release coverage is being expanded; this is not yet exhaustive. 172 company reviews are still open.

See what is being reviewed