Inference Fallback Adapter: configuration for a fallback STT model that runs server-side in LiveKit Inference, providing automatic fallback between providers. Extra fields are passed through to the provider.
Optional
Extra configuration for the model.
Model name (e.g. "deepgram/nova-3", "assemblyai/universal-streaming", "cartesia/ink-whisper").
Inference Fallback Adapter: configuration for a fallback STT model that runs server-side in LiveKit Inference, providing automatic fallback between providers. Extra fields are passed through to the provider.