Skip to main content
Fish Audio is a voice AI platform. Every core feature is available three ways: in the web app (no code), through the REST API, and via the official SDK.

​
Core features

Text to Speech

Convert text into lifelike speech with the s2.1-pro, s2-pro, and deprecated s1 models.

Speech to Text

Transcribe audio with transcribe-1-pro: multi-speaker conversations, long recordings, emotion cues, and optional timestamps.

Voice Cloning

Clone a voice instantly from a clip, or train a persistent model.

Realtime Streaming

Stream audio as it generates, for voice agents and live apps.

Manage Voices

List, inspect, update, and delete your voice models.

​
Also in the web app

These run in the browser, no code required. See the Platform guide.

Professional Voice Clone

Clone a real, verified voice at studio quality, then release it.

Voice Design

Design a voice from a plain-text description. Best for original characters.

Voice Changer

Transform existing audio into a different voice.

Story Studio

Produce multi-speaker, long-form audio: audiobooks and narration.

Music & Sound Effects

Generate music and cinematic sound effects from a prompt.

Audio Separation

Split audio into stems, and related processing utilities.

​
Models

These text-to-speech models power most capabilities:
  • s2.1-pro: the recommended production model, with improved quality, latency, and throughput over S2-Pro.
  • s2.1-pro-free: the same model at $0 for testing, prototyping, development, and smaller businesses, without TTFA or DPA guarantees.
  • s2-pro: the previous-generation S2 model, with multi-speaker and natural-language expression control.
  • s1: the previous generation, with (parenthesis) emotion tags. S1 is deprecated and will be retired on December 31, 2026. After that date, requests that specify s1 are served by s2.1-pro. See Migrate from S1.
For speech to text, select the model with the model header on POST /v1/asr:
  • transcribe-1-pro: the recommended model, for everything from short clips to multi-speaker conversations (speaker markers and speaker turns) and long recordings, with inline emotion cues. Send model: transcribe-1-pro explicitly.
  • transcribe-1: general transcription of short recordings. A request whose model header is missing or not an exact match is served by this model.
See Models Overview and Choosing a Model for the full lineup and languages, and Speech to Text for transcription formats and limits.

​
Pick your path

Use the web app

No code: generate audio, clone voices, and produce projects in your browser.

Build with the SDK

The Python library for your application.

Call the API

Raw REST and WebSocket endpoints for any language.

Use your AI coding agent

Install the Fish Audio skill so your agent writes correct code.