Build with Fish Audio

Powerful API, SDKs, and voice tools for developers to integrate AI-generated speech

Bring Voice AI to your app

Leverage productoin-ready tools to create lifelike speech, clone voices, and transcribe audio with minimal setup

RESTful API with comprehensive documentation. Support for text-to-speech, voice cloning, and speech-to-text with low latency and high quality output.

# Text to Speech API

curl -X POST https://api.fish.audio/v1/tts \

-H "Authorization: Bearer YOUR_API_KEY" \

-H "Content-Type: application/json" \

-H "model: speech-1.5" \

-d '{

"text": "Hello, world!",

"reference_id": "voice_id",

"format": "mp3"

}' \

-o output.mp3

Official Python SDK with async support, streaming capabilities, and comprehensive type hints for a seamless development experience.

# Install

pip install fish-audio-sdk

# Usage

from fish_audio_sdk import Session, TTSRequest

session = Session("your_api_key")

with open("r.mp3", "wb") as f:

for chunk in session.tts(TTSRequest(text="Hello, world!")):

f.write(chunk)

Simple, transparent pricing with pay-as-you-go model. No hidden fees, no minimum commitments. Scale as you grow.