Skip to main content
The default and recommended end-to-end configuration optimized for real-time conversation. All CVI layers are active and customizable.
  • Low utterance-to-utterance latency with Tavus defaults (see What is CVI?)
  • Best for natural humanlike interactions

CVI quickstart

​
Alternate Modes

These modes are incompatible with Tavus’s perception and speech recognition layers. For the lowest latency and the full multimodal stack (perception, turn-taking, and rendering together), we recommend the full Tavus pipeline above.

​
Echo Mode

Tavus also supports an Echo mode pipeline. It lets you send text or audio input directly to the persona for playback, bypassing most of the CVI pipeline.

​
Integration Modes

If you already run conversational AI on LiveKit or Pipecat, you can still use a Tavus replica for synchronized avatar video - see the dedicated guides for setup and API details.
  • LiveKit Agent — Tavus renders the replica in a LiveKit room alongside a LiveKit Agents voice assistant.
  • Pipecat — Tavus joins as a transport participant or supplies video via TavusVideoService while Pipecat runs the pipeline on Daily.

​
Custom LLM / Bring Your Own Logic

Use this mode to integrate a custom LLM or a specialized backend for interpreting transcripts and generating responses.
  • Adds latency due to external processing
  • Does not require an actual LLM—any endpoint that returns a compatible chat completion format can be used

Integrate your own custom LLM or logic