> For the complete documentation index, see [llms.txt](https://docs.bonzai.sh/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.bonzai.sh/product-manuals/bonzai-desktop/audio.md).

# Audio & Music

Audio mode covers spoken voice and music generation.

## Speech

Use fast speech for previews and higher-quality persona speech when voice character matters.

1. Enter the text to speak.
2. Choose the voice or persona.
3. Adjust available delivery settings.
4. Generate and listen.
5. Download or reuse the result.

Write punctuation the way you want the speaker to pause. Short paragraphs are easier to control than one long block.

## Music

Describe genre, instrumentation, tempo, emotional arc, vocal style, and lyrical theme. If lyrics are included, separate structural sections such as verse and chorus clearly.

## Companion voices

Companions can use generated speech as part of multimodal conversation. Their identity and memory provide character context; the selected speech pipeline provides the audible performance.

## Privacy

Local speech and music remain on the device unless you download, share, mint, publish, or send them through a configured workflow.