Skip to main content
This guide is for training a face through the API with video URLs. If you prefer a guided flow with upload checks and inline validation, use the PAL Maker.

​
Outcome

You will POST /v2/faces with train_video_url then poll GET /v2/faces/{face_id} until training finishes.

​
Prerequisites

  • Publicly downloadable URLs for each asset you send (for example presigned S3 GET URLs). Keep them valid for at least 24 hours after submission.

​
1. Create the face

Default model is phoenix-4. To request phoenix-3, include "model_name": "phoenix-3" in the JSON body. Personal face (training video): 
curl --request POST \
  --url https://tavusapi.com/v2/faces \
  --header 'Content-Type: application/json' \
  --header "x-api-key: $TAVUS_API_KEY" \
  --data '{
    "callback_url": "",
    "face_name": "my_replica",
    "train_video_url": "https://example.com/training-video.mp4",
  }'
Synthetic / non-human: send train_video_url 
curl --request POST \
  --url https://tavusapi.com/v2/faces \
  --header 'Content-Type: application/json' \
  --header "x-api-key: $TAVUS_API_KEY" \
  --data '{
    "callback_url": "",
    "face_name": "synthetic_replica",
    "train_video_url": "https://example.com/training-video.mp4"
  }'

​
2. Poll face status

Use Get Face: 
curl --request GET \
  --url "https://tavusapi.com/v2/faces/$REPLICA_ID" \
  --header "x-api-key: $TAVUS_API_KEY"
Training usually takes 3–4 hours. Optional: set callback_url to receive status webhooks.

​
3. Start a conversation

Generate a conversation with your face using Create Conversation 
curl --request POST \
  --url https://tavusapi.com/v2/conversations \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: $TAVUS_API_KEY" \
  --data '
{
  "face_id": $REPLICA_ID" 
}
'