Skip to main content
Use this page when you want to create a PAL and start your first Tavus conversation. If you are building a web app that creates conversations from a backend and embeds the returned conversation_url, use CVI App Quickstart.
Use the full pipeline to unlock the complete range of face capabilities - including perception and speech recognition.
1

Step 1: Create a PAL

In this example, we’ll create an interviewer PAL with the following settings:
  • A Phoenix-4 Pro face.
  • raven-1 as the perception model for visual and audio understanding.
  • sparrow-2 for fewer interruptions and graceful handling of backchannels, tuned with high patience to give interview candidates time to think.
r90bbd427f71 is the stock Anna Face ID used throughout these docs. It is a stock ID, not a placeholder. A PAL is what you build in CVI: configure its Face to define how it looks, its Voice to define how it sounds, and its other settings to shape how it thinks and acts.
Use the following request body example:
cURL
Replace <api_key> with your actual API key. You can generate one in the PAL Maker.
Tavus offers full layer customizations for your PAL. Please see the following for each layer configurations:
2

Step 2: Create Your Conversation

Create a new conversation using your newly created pal_id:
cURL
  • Replace <api_key> with your actual API key.
  • Replace <your_pal_id> with your newly created PAL ID.
3

Step 3: Join the Conversation

To join the conversation, click the link in the conversation_url field from the response:
Building an app around this flow? Follow CVI App Quickstart. React apps that want Tavus-provided UI can use the @tavus/cvi-ui component library for CVIProvider, Conversation, hooks, and server helpers.