Audio & Music Models

BonzAI supports local speech and music workflows.

Speech

• Fast speech for previews and everyday narration.

• Higher-quality persona speech when voice identity and performance matter.

• Companion voice generation inside multimodal conversations.

Music

Music generation accepts a style/production brief and optional lyrical structure. Describe genre, instrumentation, tempo, mood, vocal character, and song progression.

Generated audio remains local until you export, share, mint, publish, or use it in another connected workflow.