> ## Documentation Index
> Fetch the complete documentation index at: https://anam.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Fish Audio Integration

> Give a Fish Audio voice an interactive Anam avatar in your LiveKit agent. Learn how it works, choose how to connect Fish Audio, and build it with a coding agent.

Build the quickstart with a coding agent

Paste this prompt into your coding agent. It adapts an existing LiveKit project or asks what to build, then waits for you to add your credentials before starting the agent.

Copy prompt

Use [Fish Audio](https://fish.audio/?utm_source=anam\&utm_medium=referral) for text-to-speech in your LiveKit agent and Anam to turn that speech into an interactive avatar. You choose the speech-to-text (STT) and large language model (LLM); LiveKit runs the conversation and delivers the avatar's audio and video to your frontend.

## How it works

```text theme={"system"}
User microphone → LiveKit agent → Speech-to-text (STT) → LLM
                                                          ↓
                                                    Fish Audio TTS
                                                          ↓
                                                     Anam avatar
                                                          ↓
                                     LiveKit room → User hears and sees the avatar
```

Fish Audio turns the LLM's replies into speech. The Anam LiveKit plugin sends that audio to Anam, which joins the LiveKit room as a participant and publishes synchronized audio and avatar video. Your frontend renders the avatar participant's tracks.

> [!NOTE]
>
> Fish Audio runs inside your LiveKit agent. You don't import a voice into Anam for this Fish Audio LiveKit implementation.

## Choose how to connect Fish Audio

You can choose between two ways to implement Fish Audio with Anam. **LiveKit Inference** is the quickest: LiveKit serves Fish Audio's voices, so you only need LiveKit and Anam credentials and LiveKit bills the usage. The **[Fish Audio plugin](https://docs.fish.audio/developer-guide/integrations/livekit?utm_source=anam\&utm_medium=referral)** connects to Fish Audio with your own API key, so you're billed by Fish Audio directly and can use any voice on your account.

| | LiveKit Inference | Fish Audio plugin |
| - | - | - |
| Credentials | LiveKit Cloud only, no Fish Audio API key | `FISH_API_KEY` from [Fish Audio](https://fish.audio/?utm_source=anam\&utm_medium=referral) |
| Billing | Through your LiveKit Cloud project | Directly with Fish Audio |
| Voices | Fish Audio's default voices | Any voice your Fish Audio account can use, including custom and community voices |
| Speech-to-text | Any LiveKit Inference STT model | Fish Audio STT is also available |

The [Quickstart](https://anam.ai/docs/integrations/fish-audio/quickstart.md) uses LiveKit Inference. [Configuration](https://anam.ai/docs/integrations/fish-audio/configuration.md#use-your-own-fish-audio-api-key) shows how to switch to the plugin.

## See it in action

Try the [Fish Audio integration demo](https://anam.ai/integrations/fishaudio) to talk to an Anam avatar that speaks with Fish Audio's [Drama 3](https://fish.audio/drama-3/?utm_source=anam\&utm_medium=referral) voice model, powered by LiveKit.

## Resources

> [card] [Quickstart](https://anam.ai/docs/integrations/fish-audio/quickstart.md)
>
> Build a Python agent and connect a React frontend

> [card] [Configuration](https://anam.ai/docs/integrations/fish-audio/configuration.md)
>
> Voices, models, Fish Audio options, and deployment

> [card] [LiveKit Fish Audio docs](https://docs.livekit.io/agents/models/tts/fishaudio/)
>
> Fish Audio models, voices, and parameters in LiveKit

> [card] [Anam LiveKit plugin](https://anam.ai/docs/integrations/livekit/configuration.md)
>
> Avatar options, Director Notes, and advanced examples


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.