---
id: fish-audio-sdk
version: "1.3.0"
license: Apache-2.0
license_treatment: permissive
maintenance: active
---

# fish-audio-sdk — The official Python library for the Fish Audio API

License: permissive · Maintenance: active · Downloads: 192.1K/mo

## What it is and what it does

Fish Audio SDK is the official Python client for Fish Audio's cloud-hosted speech synthesis and recognition services. It wraps HTTP and WebSocket APIs for text-to-speech (TTS), automatic speech recognition (ASR), voice management, and account operations. The library supports both synchronous and asynchronous workflows, making it suitable for simple scripts and production applications alike.

The SDK handles authentication via API key, provides typed request/response objects through pydantic, and includes utilities for audio playback and file I/O. It exposes core resources for converting text to speech with custom voices, transcribing audio files, cloning voices from samples, and checking account credits. Real-time streaming is supported via WebSocket for conversational AI and live applications.

Use it for:

- Build a chatbot or voice assistant that speaks responses in real time using TTS streaming
- Transcribe recorded audio files or live speech streams for meeting notes or accessibility
- Clone a custom voice from a sample recording and reuse it across multiple TTS requests
- Integrate speech synthesis into a web or mobile app backend with async/await support
- Monitor account usage and credit balance programmatically before running large synthesis jobs

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

Official Python client for the Fish Audio API, providing text-to-speech, speech-to-text, voice cloning, and real-time streaming capabilities with both synchronous and asynchronous interfaces.

Yes. The package is actively maintained, has no known vulnerabilities, installs cleanly with low friction, and is licensed permissively under Apache-2.0. It is the official SDK for Fish Audio's API, so it is the natural choice if you need to integrate Fish Audio services into a Python application. Verify that Fish Audio's pricing and rate limits fit your use case before committing.

## Install

pip install fish-audio-sdk
uv add fish-audio-sdk
poetry add fish-audio-sdk

## Installing fish-audio-sdk

Before you install: Low install friction with a pure-Python wheel distribution. Active maintenance with a recent commit on 2026-07-31 and steady release cadence. Supports Python 3.9 through 3.14.

License in practice: Licensed under Apache-2.0 (permissive), allowing commercial use, modification, and distribution with minimal restrictions—suitable for most projects.

Quickstart:

pip install fish-audio-sdk

from fish_audio_sdk import FishAudio

client = FishAudio(api_key="your_api_key")
audio = client.tts.convert(text="Hello, world!")

Requires a valid Fish Audio API key from fish.audio/app/api-keys; API calls are rate-limited and consume account credits.

Verify before relying:

- Exact rate limits and quota behavior for different account tiers
- Performance characteristics for large-scale batch TTS or ASR operations
- Latency guarantees for real-time streaming endpoints
- Whether the import path is fish_audio_sdk or fishaudio in version 1.3.0

## Package facts

- License: Apache-2.0 (permissive)
- Python support: supports_current
- Install friction: low
- Maintenance: active
- Downloads: 192.1K/month (top 15,000 on PyPI)
- Known vulnerabilities: none known

## Tags

text-to-speech API client, speech-to-text transcription, voice cloning SDK, audio streaming Python, fish audio API, TTS with voice control, real-time audio synthesis, speech-synthesis, voice-cloning, async-support

[View on SkillFed](https://skillfed.io/packages/fish-audio-sdk) · [View on PyPI](https://pypi.org/project/fish-audio-sdk/)