Requirements
- Google AI Studio / Gemini API key with access to the Live API
- Optional Context for system prompt / instructions
Setup
1. Register your Gemini API key as a secret:Configuration
Models
Currently supported models:gemini-3.1-flash-live-preview(default)gemini-2.5-flash-native-audio-preview-12-2025
Voices
Currently supported voices:Achernar, Achird, Algenib, Algieba, Alnilam, Aoede, Autonoe, Callirrhoe, Charon, Despina, Enceladus, Erinome, Fenrir, Gacrux, Iapetus, Kore, Laomedeia, Leda, Orus, Pulcherrima, Puck, Rasalgethi, Sadachbia, Sadaltager, Schedar, Sulafat, Umbriel, Vindemiatrix, Zephyr, Zubenelgenubi. See Google’s Gemini Live API voice reference for the authoritative list and characteristics.
How it works
- A WebRTC room is created by LiveAvatar on your behalf (no WebSocket endpoint returned)
- LiveAvatar bridges your session to the Gemini Live API using your credentials
- User audio is streamed to Gemini Live; the model’s audio drives avatar lip sync
For protocol-level details — turn detection, tool calls, input/output modalities — see the Gemini Live API docs.
Billing
- LiveAvatar: 1 credit per session minute (avatar video only)
- Gemini: charged separately against your Google account for Live API usage