# Build with Fish Audio

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

## Bring Voice AI to your app

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

### API

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

[View API Documentation](https://docs.fish.audio/api-reference/introduction)

# Text to Speech API

```bash
curl -X POST https://api.fish.audio/v1/tts \
-H "Authorization: Bearer $FISH_API_KEY" \
-H "Content-Type: application/json" \
-H "model: s1" \
-d '{"text": "Hello! Welcome to Fish Audio."}' \
--output welcome.mp3
```

### Python SDK

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

[View on GitHub](https://github.com/fishaudio/fish-audio-python)

# Install

```bash
pip install fish-audio-sdk
```

# Usage

```python
from fishaudio import FishAudio
from fishaudio.utils import save

client = FishAudio(api_key="your_api_key_here")

audio = client.tts.convert(text="(surprised) Wow, you are quite handsome!")

save(audio, "welcome.mp3")
```

### JavaScript SDK

Official JavaScript SDK with TypeScript support, streaming capabilities, and a simple API for integrating Fish Audio into your Node.js applications.

[View on GitHub](https://github.com/fishaudio/fish-audio-typescript)

# Install

```bash
npm install fish-audio
```

# Usage

```javascript
import { FishAudioClient, play } from "fish-audio";

const fishAudio = new FishAudioClient({ apiKey: "your_api_key_here" });

const request = { text: "(excited) Oh wow Kyle that is amazing!" };

const audio = await fishAudio.textToSpeech.convert(request);

await play(audio);
```

### API Pricing

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

[View Full Pricing](https://docs.fish.audio/developer-guide/models-pricing/pricing-and-rate-limits)

| Model Type | Model Name | Pricing |
| --- | --- | --- |
| TTS | S2 Pro | $15.00 / million UTF-8 bytes |
| TTS | S1 | $15.00 / million UTF-8 bytes |
| ASR | transcribe-1 | $0.36 / hour |

## Create with the most expressive AI voices

[Start free now](/content/auth/?redirect=/app/index.html)