Fish Audio

Real-time text-to-speech service using Fish Audio’s WebSocket API

Overview

FishAudioTTSService provides real-time text-to-speech synthesis through Fish Audio’s WebSocket-based streaming API. The service offers custom voice models, prosody controls, and multiple audio formats optimized for conversational AI applications with low latency.

Fish TTS API Reference

Pipecat’s API methods for Fish Audio TTS integration

Example Implementation

Complete example with custom voice model

Fish Audio Documentation

Official Fish Audio documentation

Voice Models

Create and manage custom voice models

Installation

To use Fish Audio services, install the required dependencies:

pip install "pipecat-ai[fish]"

Prerequisites

Fish Audio Account Setup

Before using Fish Audio TTS services, you need:

1. Fish Audio Account: Sign up at Fish Audio Console
2. API Key: Generate an API key from your account dashboard
3. Voice Models: Create or select custom voice models for synthesis

Required Environment Variables

• FISH_API_KEY: Your Fish Audio API key for authentication

Configuration

FishAudioTTSService

api_key · str · required

Fish Audio API key for authentication.

reference_id · str · default: "None"

Reference ID of the voice model to use for synthesis.

model_id · str · default: "s1"

Fish Audio TTS model to use.

output_format · str · default: "pcm"

Audio output format. Options: "pcm", "opus", "mp3", "wav".

sample_rate · int · default: "None"

Output audio sample rate in Hz. When None, uses the pipeline’s configured sample rate.

params · InputParams · default: "None"

Runtime-configurable voice settings. See InputParams below.

InputParams

Voice and generation settings that can be set at initialization via the params constructor argument.

Parameter	Type	Default	Description
language	Language	Language.EN	Language for synthesis.
latency	str	"normal"	Latency mode: "normal" or "balanced".
normalize	bool	True	Whether to normalize audio output.
prosody_speed	float	1.0	Speech speed multiplier (0.5-2.0).
prosody_volume	int	0	Volume adjustment in dB.

Usage

Basic Setup

from pipecat.services.fish import FishAudioTTSService

tts = FishAudioTTSService(
    api_key=os.getenv("FISH_API_KEY"),
    reference_id="your-voice-reference-id",
)

With Prosody Controls

tts = FishAudioTTSService(
    api_key=os.getenv("FISH_API_KEY"),
    reference_id="your-voice-reference-id",
    model_id="s1",
    params=FishAudioTTSService.InputParams(
        prosody_speed=1.2,
        prosody_volume=3,
        latency="balanced",
    ),
)

Notes

• reference_id required: You must specify either reference_id (preferred) or the deprecated model parameter. Passing both raises a ValueError.
• Model switching: Changing the model via set_model() automatically disconnects and reconnects the WebSocket with the new model configuration.

Event Handlers

Fish Audio TTS supports the standard service connection events:

Event	Description
on_connected	Connected to Fish Audio WebSocket
on_disconnected	Disconnected from Fish Audio WebSocket
on_connection_error	WebSocket connection error occurred

@tts.event_handler("on_connected")
async def on_connected(service):
    print("Connected to Fish Audio")