Fish Audio

Fish Audio is an AI voice platform offering text-to-speech, voice cloning, speech-to-text, voice changing, and audio storytelling capabilities. The platform hosts a library of over two million voices across 30+ languages and is built around the Fish Speech open-source TTS model and the proprietary Fish Audio S2-Pro model. Fish Audio exposes a public REST API at api.fish.audio with first-party Python, Go, and TypeScript SDKs and supports voice cloning from as little as fifteen seconds of reference audio. The developer surface emphasizes ultra-low latency streaming, emotion control, and pay-as-you-go pricing for both prototype and production workloads.

Fish Audio publishes 5 API contracts indexed on the APIs.io network, including Asr API, Model API, Tts API, and 2 more. Tagged areas include Voice, Text-to-Speech, Speech-to-Text, Voice Cloning, and Audio.

Fish Audio’s developer surface includes engineering blog, authentication, documentation, pricing, and 13 more developer resources.

🌐 Visit website 📡 Profile data on GitHub

29.5/100 thin ▼ -6.0 Agent 43/100 agent ready Front door AI 6/6 dominant saas Full breakdown ↓
scored 2026-10-17 · rubric v0.24.0

AccessFreeSelf serve⚡ Free to try

1 published contract 1 MCP Servers

Voice Text-to-Speech Speech-to-Text Voice Cloning Audio Generative AI Multilingual Streaming SDK Open Source

Kin Score

Kin Score How this is scored →
scored 2026-10-17 · rubric v0.24.0

Composite quality — 29.5/100 · thin

Contract Quality 9.0 / 19

Developer Ergonomics 7.3 / 15

Access Clarity 0.8 / 15

Operational Transparency 0.8 / 10

Contract Governance 0.0 / 9

Discoverability 5.6 / 8

Regulatory Posture 1.6 / 15

Create-or-Update Ergonomics 0.0 / 10

Agent readiness — 43/100 · agent ready

Machine-Readable Contract 18 / 18

Agentic Access Contract 10 / 10

Documented Reversibility 0 / 6

MCP Server 12 / 12

Machine-Readable Auth 10 / 10

Idempotency 0 / 9

Stable Error Semantics 0 / 8

Request/Response Examples 0 / 7

Rate-Limit Signaling 7 / 7

Typed Event Surface 0 / 6

Agent Skills 0 / 5

Well-Known Catalog 0 / 4

Consent & Bot Identity 0 / 3

A2A Agent Card 0 / 8

Dry-Run / Simulate Mode 0 / 4

Delegated User Identity 6 / 6

Protected Resource Metadata 5 / 5

Registration Without a Human 6 / 6

Agentic Commerce Well-Known Document 0 / 5

Regulatory Posture applies to this provider. Its tags matched the AI & Biometrics regime, so Regulatory Posture carries 15 points of the composite. If this regime is wrong for your business, say so on your provider repo — the applicability map is public and we will correct it.

Create-or-Update Ergonomics applies to this provider. This API accepts writes, so it carries 10 points of the composite. It is scored from the published contracts themselves: whether a caller can create-or-update in one call, whether the write accepts a key the caller already holds, and whether the response says which branch ran. Without that, every write needs a search-and-branch in front of it, and the first time that check is skipped a duplicate record is created. Scored against the observed mean rather than raw — a provider at the catalog average is unchanged by this facet, not penalised by it.

The six quality facets above are damped to 75 points between them, because the conditional facet above carries the other 25. That is why each facet's contribution is shown against a damped maximum: raising a quality facet moves the composite by 75% of its nominal weight, not 100%. The full arithmetic is at apis.io/rating/.

Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. Every facet and dimension name above is a link: it opens that measurement's own page — what it means, the exact checks that feed it, how the whole catalog distributes on it, and the providers at the top of it. This rating is computed from github.com/api-evangelist/fish-audio: open an issue to ask a question, or submit a pull request to add artifacts. Submit an artifact on GitHub — free → Manage your own listing — the Influence plan, $499/mo →

Markets this provider is in provisional

The Kin Score Market layer reads a provider inside its market: its position, and how deep its integrations go. Depth is only comparable within a position. Provisional and unweighted: not part of the Kin Score or agent readiness.

Market	Position	Depth	Registered MCP server	Declares compatibility
Speech and Voice AI	covered	51.7	-	-

Registered MCP server and declares compatibility are report only — not weighted. Undeclared means we found nothing we can read, so there is no number: we never infer integrations.

APIs 5

Individual APIs this provider publishes, each with its own machine-readable definition.

Fish Audio API

The Fish Audio API provides RESTful access to text-to-speech, speech-to-text, voice cloning, and voice management capabilities backed by the Fish Audio S2-Pro model. Endpoints s...

Fish Audio Asr API

The Asr API from Fish Audio — 1 operation(s) for asr.

Fish Audio Model API

The Model API from Fish Audio — 2 operation(s) for model.

Fish Audio Tts API

The Tts API from Fish Audio — 2 operation(s) for tts.

Fish Audio Wallet API

The Wallet API from Fish Audio — 2 operation(s) for wallet.

Open Collections 6

Open, tool-agnostic API collections (OpenAPI-derived and Bruno).

API Collection

OPEN COLLECTION

Fish Audio Asr API

OPEN COLLECTION

Fish Audio Asr Model API

OPEN COLLECTION

Fish Audio Asr Tts API

OPEN COLLECTION

Fish Audio Asr Wallet API

OPEN COLLECTION

Fish Audio API

OPEN COLLECTION

MCP Servers 1

Model Context Protocol servers that expose these APIs to AI agents.

Fish Audio MCP Server

Remote MCP server at api.fish.audio over HTTP.

MCP SERVER

Pricing Plans 1

Published pricing tiers and plan structures.

Fish Audio Plans Pricing

1 plans

PLANS

Rate Limits 1

Documented rate limits and quota policies.

Fish Audio Rate Limits

2 limits

RATE LIMITS

FinOps 1

Cost, billing, and metering signals for API financial operations.

Fish Audio Finops

FINOPS

Security Posture 2

Authentication, domain security, vulnerability disclosure, and trust-center signals.

Fish Audio Authentication

http · 1 scheme

SECURITY

Fish Audio Domain Security

TLSv1.3 · HSTS · DMARC

SECURITY

Agentic Access 1

Recommended x-agentic-access execution contracts for AI agents.

Fish Audio Agentic Access

10 operations · 6 acting

AGENTIC

Resources

Get Started 1

Portal, sign-up, and the first successful call

DeveloperPortal

DeveloperPortal

Documentation 1

Reference material describing how the API behaves

Documentation

Documentation

Agent Surfaces 2

MCP servers, agent skills, and machine-readable catalogs

AgenticAccess

AgenticAccess

LlmsText

LlmsText

Build 1

SDKs, sample code, and the tooling you integrate with

GitHubOrganization

GitHubOrganization

Access & Security 2

Authentication, authorization, and security posture

DomainSecurity

DomainSecurity

Authentication

Authentication

Operate 2

Status, limits, changes, and where to get help

RateLimits

RateLimits

Discord

Discord

Commercial 3

Pricing, plans, and the legal terms of use

Plans

Plans

FinOps

FinOps

Pricing

Pricing

Company 3

The organization behind the API

Blog

Blog

Website

Website

Twitter

Twitter

Other 2

Properties that don't map to a standard resource type

Playground

Playground

OpenSourceModel

OpenSourceModel

Source (apis.yml)

aid: fish-audio
name: Fish Audio
description: Fish Audio is an AI voice platform offering text-to-speech, voice cloning, speech-to-text, voice changing, and
  audio storytelling capabilities. The platform hosts a library of over two million voices across 30+ languages and is built
  around the Fish Speech open-source TTS model and the proprietary Fish Audio S2-Pro model. Fish Audio exposes a public REST
  API at api.fish.audio with first-party Python, Go, and TypeScript SDKs and supports voice cloning from as little as fifteen
  seconds of reference audio. The developer surface emphasizes ultra-low latency streaming, emotion control, and pay-as-you-go
  pricing for both prototype and production workloads.
type: Index
deliveryModel:
  model: saas
  open_source: false
  commercial: true
  callable_host: true
  label: Hosted service · you call their endpoint
  confidence: high
  source:
  - openapi
  - pricing
  generated: '2026-08-28'
  method: derived
accessModel:
  pricing: free
  onboarding: self-serve
  trial: false
  try_now: true
  public: false
  label: Free · Self-serve signup
  confidence: medium
  source:
  - plans
  - authentication
  - security
  generated: '2026-09-03'
  method: derived
position: Producing
access: 3rd-Party
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/icons/fish-audio.png
x-docs-platform: mintlify
x-docs-platform-confidence: medium
x-docs-platform-checked: 2026-10-03
x-docs-hosting: vercel
tags:
- Voice
- Text-to-Speech
- Speech-to-Text
- Voice Cloning
- Audio
- Generative AI
- Multilingual
- Streaming
- SDK
- Open Source
tags_raw:
- Voice
- Text to Speech
- Speech to Text
- Voice Cloning
- Audio
- Generative AI
- Multilingual
- Streaming
- SDK
- Open Source
- Open-Source
url: https://raw.githubusercontent.com/api-evangelist/fish-audio/refs/heads/main/apis.yml
created: '2026-05-23'
modified: '2026-10-06'
specificationVersion: '0.23'
apis:
- aid: fish-audio:fish-audio-api
  name: Fish Audio API
  description: The Fish Audio API provides RESTful access to text-to-speech, speech-to-text, voice cloning, and voice management
    capabilities backed by the Fish Audio S2-Pro model. Endpoints support streaming low-latency generation, multilingual synthesis
    across 30+ languages, emotion control, and on-the-fly custom voice creation from short reference clips. The API is consumed
    through the Fish Audio Python, Go, and TypeScript SDKs and a community of integrations including n8n.
  humanURL: https://docs.fish.audio
  baseURL: https://api.fish.audio
  tags:
  - Text-to-Speech
  - Voice Cloning
  - Speech-to-Text
  - Streaming
  - REST
  - Audio
  tags_raw:
  - Text to Speech
  - Voice Cloning
  - Speech to Text
  - Streaming
  - REST
  - Audio
  properties:
  - type: Documentation
    url: https://docs.fish.audio
  - type: GettingStarted
    url: https://docs.fish.audio/quickstart
  - type: Playground
    url: https://fish.audio/discovery
  - type: SDKs
    url: https://github.com/fishaudio/fish-audio-python
  - type: SDKs
    url: https://github.com/fishaudio/fish-audio-go
  - type: GitHubOrganization
    url: https://github.com/fishaudio
  features:
  - name: Text-to-Speech Generation
    description: Synthesize natural, emotionally expressive speech from text using the Fish Audio S2-Pro model across 30+
      languages.
  - name: Voice Cloning
    description: Create custom voice models from as little as 15 seconds of reference audio for downstream TTS.
  - name: Speech-to-Text Transcription
    description: Transcribe audio with multispeaker detection and emotion tagging metadata.
  - name: Streaming Audio
    description: Low-latency streaming responses suitable for real-time agent, IVR, and live narration use cases.
  - name: Emotion and Prosody Control
    description: Inline emotion tags (angry, sad, excited) and special effects (laughing, sobbing) for expressive output.
  - name: Multilingual Synthesis
    description: Native support for English, Mandarin, Japanese, Korean, and more than 25 additional languages.
  - name: Voice Library
    description: Access to a hosted library of more than two million pre-built voices for instant TTS generation.
  useCases:
  - name: Audiobook and Podcast Production
    description: Generate full-length narrated content with multi-character voices via Story Studio workflows.
  - name: Conversational Agents and IVR
    description: Power voice-first agents and interactive voice response systems with low-latency synthesis.
  - name: Gaming NPC Dialogue
    description: Create dynamic in-game character voices and barks without manual voice-over sessions.
  - name: Video and Content Localization
    description: Dub and localize video, social, and marketing content across dozens of languages.
  - name: Accessibility Tooling
    description: Embed expressive screen reading and assistive voice output in accessibility products.
  integrations:
  - name: Python SDK
  - name: Go SDK
  - name: TypeScript SDK
  - name: n8n
  - name: LangChain
  - name: Hugging Face
  - name: Discord
  authentication:
  - type: API Key
    description: Requests authenticate using a Bearer API key issued from the Fish Audio dashboard.
- aid: fish-audio:fish-audio-asr-api
  name: Fish Audio Asr API
  description: The Asr API from Fish Audio — 1 operation(s) for asr.
  humanURL: https://docs.fish.audio
  baseURL: https://api.fish.audio
  tags:
  - ASR
  tags_raw:
  - Asr
  properties:
  - type: OpenAPI
    url: openapi/fish-audio-asr-api-openapi.yml
- aid: fish-audio:fish-audio-model-api
  name: Fish Audio Model API
  description: The Model API from Fish Audio — 2 operation(s) for model.
  humanURL: https://docs.fish.audio
  baseURL: https://api.fish.audio
  tags:
  - Model
  properties:
  - type: OpenAPI
    url: openapi/fish-audio-model-api-openapi.yml
- aid: fish-audio:fish-audio-tts-api
  name: Fish Audio Tts API
  description: The Tts API from Fish Audio — 2 operation(s) for tts.
  humanURL: https://docs.fish.audio
  baseURL: https://api.fish.audio
  tags:
  - TTS
  tags_raw:
  - Tts
  properties:
  - type: OpenAPI
    url: openapi/fish-audio-tts-api-openapi.yml
- aid: fish-audio:fish-audio-wallet-api
  name: Fish Audio Wallet API
  description: The Wallet API from Fish Audio — 2 operation(s) for wallet.
  humanURL: https://docs.fish.audio
  baseURL: https://api.fish.audio
  tags:
  - Wallets
  tags_raw:
  - Wallet
  properties:
  - type: OpenAPI
    url: openapi/fish-audio-wallet-api-openapi.yml
common:
- type: Plans
  url: plans/fish-audio-plans-pricing.yml
- type: RateLimits
  url: rate-limits/fish-audio-rate-limits.yml
- type: FinOps
  url: finops/fish-audio-finops.yml
- url: https://fish.audio/blog/
  type: Blog
- type: AgenticAccess
  url: agentic-access/fish-audio-agentic-access.yml
- type: DomainSecurity
  url: security/fish-audio-domain-security.yml
- type: Authentication
  url: authentication/fish-audio-authentication.yml
- type: Website
  url: https://fish.audio
- type: Documentation
  url: https://docs.fish.audio
- type: DeveloperPortal
  url: https://fish.audio/go-api
- type: Playground
  url: https://fish.audio/discovery
- type: Pricing
  url: https://fish.audio/pricing
- type: GitHubOrganization
  url: https://github.com/fishaudio
- type: OpenSourceModel
  url: https://github.com/fishaudio/fish-speech
- type: Discord
  url: https://discord.gg/Es5qTB9BcN
- type: Twitter
  url: https://twitter.com/FishAudio
- type: LlmsText
  url: https://docs.fish.audio/llms.txt
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com

Work with this as data

Every provider here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for providers

9 MCP tools reach this

find_providersBrowse and filter every provider in the catalog.
get_provider_artifactsEvery artifact this provider publishes, grouped by type.
get_provider_operationsEvery operation across all of their OpenAPIs — one call instead of parsing every spec.
get_provider_toolsEvery MCP tool they ship, with the operation each wraps.
get_provider_evidenceHow each part of their score was established. Free — the basis for a claim should not sit behind it.
get_provider_ratingPRO — composite, band, trend and facet scores.
apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
resolveTurn a domain, URL or GitHub org into the provider it belongs to.
find_cohortsEvery scored population of providers in the catalog.

All 92 tools →

Call it yourself

curl for this page

This provider

curl "https://apis.io/api/v1/providers/fish-audio"

All providers

curl "https://apis.io/api/v1/providers?limit=25"

Every operation they expose

curl "https://apis.io/api/v1/providers/fish-audio/operations?limit=25"

How their score was established

curl "https://apis.io/api/v1/providers/fish-audio/evidence"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.