# Audio & Music

BonzAI provides text-to-speech and music generation pipelines, all running locally.

## Text-to-Speech

### Turbo TTS (Kokoro)

Fast, high-quality speech synthesis. Best for real-time companion voice responses.

```
POST http://localhost:65000/audio/turbo
```

### Quality TTS (Qwen3-TTS)

Persona-based speech synthesis with fine-grained control over voice characteristics. Higher quality, slower generation.

```
POST http://localhost:65000/audio/quality/persona
```

## Music Generation (ACE-Step)

Generate original music with lyrics using the ACE-Step model.

```
POST http://localhost:65000/audio/music
```

## Companion Voice Pipeline

In the roleplay system, companions use a multi-modal pipeline:

1. **Text response** generated by the selected LLM
2. **TTS** converts the response to speech (Qwen3-TTS for quality, Kokoro for speed)
3. Audio plays back in the chat interface

Each companion can have a distinct voice persona based on their personality and gender.

## Minting Audio NFTs

Generated audio can be minted on Base or LUKSO. Requires **LVL2** (5,000 BONZAI held).


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.bonzai.sh/ai-generation/audio.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.