Fish Audio

Fish Audio Tts API

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

GitHub OpenAPI

Operations 2

POST /v1/tts Generate speech from text #
POST /v1/tts/stream/with-timestamp Stream TTS with per-chunk timestamps (Server-Sent Events) #

Specifications

⚙
OpenAPI
https://raw.githubusercontent.com/api-evangelist/fish-audio/refs/heads/main/openapi/fish-audio-tts-api-openapi.yml

Work with this as data

Every API 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 apis

7 MCP tools reach this
  • find_apisBrowse and filter every API in the catalog.
  • get_api_artifactsOne API's artifacts, grouped by type.
  • get_openapiThe primary OpenAPI for this API.
  • find_similar_apisAPIs that look like this one.
  • 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 API 
curl "https://apis.io/api/v1/apis/fish-audio-tts-api"
All apis 
curl "https://apis.io/api/v1/apis?limit=25"

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.

OpenAPI Specification

fish-audio-tts-api-openapi.yml Raw ↑ 
openapi: 3.2.0
info:
  title: Fish Audio Asr Tts API
  description: Fish Audio is an AI voice platform offering text-to-speech, voice cloning, speech-to-text, and voice model management. Authentication is by API key issued at https://fish.audio/app/api-keys and presented as a Bearer token.
  version: '1.0'
  contact:
    name: Fish Audio
    url: https://docs.fish.audio
servers:
- url: https://api.fish.audio
  description: Production
security:
- bearerAuth: []
tags:
- name: Tts
paths:
  /v1/tts:
    post:
      summary: Generate speech from text
      operationId: textToSpeech
      parameters:
      - name: model
        in: header
        required: false
        description: TTS model variant (s1 or s2-pro)
        schema:
          type: string
          enum:
          - s1
          - s2-pro
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
              - text
              properties:
                text:
                  type: string
                reference_id:
                  type: string
                  description: ID of a voice model to use
                format:
                  type: string
                  enum:
                  - mp3
                  - wav
                  - pcm
                  - opus
                  default: mp3
                latency:
                  type: string
                  enum:
                  - normal
                  - balanced
                prosody:
                  type: object
                  properties:
                    speed:
                      type: number
                    volume:
                      type: number
                chunk_length:
                  type: integer
      responses:
        '200':
          description: Audio stream
          content:
            audio/mpeg:
              schema:
                type: string
                format: binary
      tags:
      - Tts
  /v1/tts/stream/with-timestamp:
    post:
      summary: Stream TTS with per-chunk timestamps (Server-Sent Events)
      operationId: textToSpeechStreamWithTimestamp
      parameters:
      - name: model
        in: header
        required: false
        schema:
          type: string
          enum:
          - s1
          - s2-pro
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
              - text
              properties:
                text:
                  type: string
                reference_id:
                  type: string
                chunk_length:
                  type: integer
      responses:
        '200':
          description: SSE stream of audio chunks plus timing metadata
          content:
            text/event-stream:
              schema:
                type: string
      tags:
      - Tts
components:
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer