Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.tavus.io/llms.txt

Use this file to discover all available pages before exploring further.

​
Create an Audio Only Conversation

All features in the persona’s pipeline, including STT, Perception, and TTS, remain fully active in audio-only mode. The only change is that replica video rendering is not included.
1

Step 1: Create your Audio Only Conversation

In this example, we will use stock persona ID pcb7a34da5fe (Sales Development Rep).
To enable audio-only mode, set the audio_only parameter to true when creating the conversation:
cURL
curl --request POST \
  --url https://tavusapi.com/v2/conversations \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api_key>' \
  --data '{
  "persona_id": "pcb7a34da5fe",
  "audio_only": true
}'
Replace <api_key> with your actual API key. You can generate one in the Developer Portal.
2

Step 2: Join the Conversation

To join the conversation, click the link in the conversation_url field from the response:
{
    "conversation_id": "cd7e3eac05ede40c",
    "conversation_name": "New Conversation 1751268887110",
    "conversation_url": "<conversation_link>",
    "status": "active",
    "callback_url": "",
    "created_at": "2025-06-30T07:34:47.131571Z"
}