AI avatar video generation service for creating realistic talking avatars
TavusVideoService
integrates with Tavus to generate AI-powered video avatars that speak your text-to-speech output in real-time. The service takes audio input and produces synchronized video of a realistic avatar speaking, enabling engaging conversational AI experiences with visual presence.
TAVUS_API_KEY
- Your Tavus API keyTAVUS_REPLICA_ID
- ID of your trained voice replicaTTSAudioRawFrame
- Text-to-speech audio to be spoken by the avatarStartInterruptionFrame
- Signals conversation interruptionEndFrame
- Signals end of conversationOutputImageRawFrame
- Generated avatar video framesOutputAudioRawFrame
- Synchronized audio from the avatarStartInterruptionFrame
- Forwarded interruption signals