Fish Audio website screenshot

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.

1 APIs 0 Features
VoiceText to SpeechSpeech to TextVoice CloningAudioGenerative AIMultilingualStreamingSDKOpen Source

APIs

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...

Collections

Pricing Plans

Fish Audio Plans Pricing

1 plans

PLANS

Rate Limits

Fish Audio Rate Limits

2 limits

RATE LIMITS

FinOps

Resources

🔗
Website
Website
🔗
Documentation
Documentation
🌐
DeveloperPortal
DeveloperPortal
🔗
Playground
Playground
💰
Pricing
Pricing
👥
GitHubOrganization
GitHubOrganization
🔗
OpenSourceModel
OpenSourceModel
🔗
Discord
Discord
🔗
Twitter
Twitter
🔗
LlmsText
LlmsText

Sources

Raw ↑
opencollection: 1.0.0
info:
  name: Fish Audio API
  version: '1.0'
request:
  auth:
    type: bearer
    token: '{{bearerToken}}'
items:
- info:
    name: Generate speech from text
    type: http
  http:
    method: POST
    url: https://api.fish.audio/v1/tts
    headers:
    - name: model
      value: ''
    body:
      type: json
      data: '{}'
  docs: Generate speech from text
- info:
    name: Stream TTS with per-chunk timestamps (Server-Sent Events)
    type: http
  http:
    method: POST
    url: https://api.fish.audio/v1/tts/stream/with-timestamp
    headers:
    - name: model
      value: ''
    body:
      type: json
      data: '{}'
  docs: Stream TTS with per-chunk timestamps (Server-Sent Events)
- info:
    name: Speech-to-text
    type: http
  http:
    method: POST
    url: https://api.fish.audio/v1/asr
    body:
      type: multipart-form
      data:
      - name: audio
        type: text
        value: ''
      - name: language
        type: text
        value: ''
      - name: ignore_timestamps
        type: text
        value: ''
  docs: Speech-to-text
- info:
    name: List voice models
    type: http
  http:
    method: GET
    url: https://api.fish.audio/model
    params:
    - name: page_size
      value: ''
      type: query
    - name: page_number
      value: ''
      type: query
    - name: title
      value: ''
      type: query
    - name: tag
      value: ''
      type: query
    - name: self
      value: ''
      type: query
    - name: author_id
      value: ''
      type: query
    - name: language
      value: ''
      type: query
    - name: title_language
      value: ''
      type: query
    - name: sort_by
      value: ''
      type: query
  docs: List voice models
- info:
    name: Create a voice clone model
    type: http
  http:
    method: POST
    url: https://api.fish.audio/model
    body:
      type: multipart-form
      data:
      - name: title
        type: text
        value: ''
      - name: description
        type: text
        value: ''
      - name: voices
        type: text
        value: ''
      - name: texts
        type: text
        value: ''
      - name: tags
        type: text
        value: ''
      - name: visibility
        type: text
        value: ''
      - name: cover_image
        type: text
        value: ''
  docs: Create a voice clone model
- info:
    name: Get a voice model
    type: http
  http:
    method: GET
    url: https://api.fish.audio/model/:id
    params:
    - name: id
      value: ''
      type: path
  docs: Get a voice model
- info:
    name: Update a voice model
    type: http
  http:
    method: PATCH
    url: https://api.fish.audio/model/:id
    params:
    - name: id
      value: ''
      type: path
    body:
      type: json
      data: '{}'
  docs: Update a voice model
- info:
    name: Delete a voice model
    type: http
  http:
    method: DELETE
    url: https://api.fish.audio/model/:id
    params:
    - name: id
      value: ''
      type: path
  docs: Delete a voice model
- info:
    name: Get user package / balance / subscription
    type: http
  http:
    method: GET
    url: https://api.fish.audio/wallet/:user_id/package
    params:
    - name: user_id
      value: ''
      type: path
  docs: Get user package / balance / subscription
- info:
    name: Get API credit balance
    type: http
  http:
    method: GET
    url: https://api.fish.audio/wallet/:user_id/api-credit
    params:
    - name: user_id
      value: ''
      type: path
    - name: check_free_credit
      value: ''
      type: query
    - name: team_id
      value: ''
      type: query
  docs: Get API credit balance
bundled: true