You can record the Replica training video directly in the Developer Portal or upload a pre-recorded one via the API.

​
Talking Head Replica

​
Environment

  • Record in a quiet, well-lit space with no background noise or movement.
  • Use diffuse lighting to avoid shadows on your face.
  • Choose a simple background and avoid any moving people or objects.

​
Camera

  • Place the camera at eye level and ensure your face fills at least 25% of the frame.
  • Use a desktop recording app (e.g., QuickTime on Mac or Camera on Windows) — avoid browser-based tools.

​
Microphone

  • Use your device’s built-in microphone.
  • Avoid high-end mics or wireless earbuds like AirPods.
  • Turn off audio effects like noise suppression or EQ adjustments.

​
Yourself

✅ Do❌ Don’t
Keep your full head visible, with a clear view of your faceWear clothes that blend into the background
Ensure your face and upper body are in sharp focusWear accessories like hats, thick glasses, or earrings
If using smartphone, make sure you follow the same framing/distance from the cameraTurn your head away from the camera
Tuck back any hair covering your faceBlock your chin or mouth with your microphone
Sit upright in a stable, seated positionStand or shift positions during the video

​
Video Format

If you’re uploading a pre-recorded training video via our API, ensure it meets the following requirements:
  • Minimum FPS: 25 fps
  • Accepted formats:
    • webm
    • mp4 with H.264 video codec and AAC audio codec
  • Maximum file size: 750MB
  • Minimum resolution: 720p
If you’re creating a personal replica, you must include a verbal consent statement in the video. This ensures ethical use and compliance with data protection laws. Steps:
  • Begin with a big smile and look directly into the camera for one second.
  • Clearly read the following script:
I, (your name), am currently speaking and give consent to Tavus to create an AI clone of me by using the audio and video samples I provide. I understand that this AI clone can be used to create videos that look and sound like me.
This step is only required for personal replicas. If you’re creating an AI replica, you can skip this video.

​
Recording Your Training Video

Your video must be one continuous shot, containing:
Pro tips:
  • Keep body and head movements subtle
  • Avoid heavy hand gestures
  • Only one person should appear in the video
1

1 Minute of Talking

  • Smile widely for at least 2 seconds.
  • Look directly at the camera, positioned just below eye level.
  • Speak casually, as if talking to a friend.
  • Pause briefly (close lips) every 1–2 sentences.
  • Minimize body movement.
  • Avoid hand gestures at all times.
  • Sample script:
For the next 2 minutes, I’ll read you a story that will for sure make you smile and feel good. I will be relaxed and keep a happy face while reading. I will also read this story at a faster pace than I normally speak. I will close my lips fully after every sentence. I will read this script in a casual and conversational tone as if I am telling a story to my friend.

The sun was shining brightly, casting a warm glow over the park as Emma, Jake, and Sophie spread out their picnic blanket. Now I will close my lips fully.

Emma looked around, her face beaming with excitement. "Can you believe how perfect today is?" she exclaimed. "The sun is shining, and the weather is just right!" Her enthusiasm was contagious, and Jake couldn't help but smile as he laid back on the blanket, soaking in the sunlight. Now I will close my lips fully after this sentence.

Jake nodded in agreement, a relaxed grin spreading across his face. "It really is," he said. "Days like this remind me why I love summer. I will close my lips fully after this sentence.

Sophie, always the energetic one, jumped up from the blanket with a burst of excitement. "And we have the whole day to ourselves!" she declared. "So many possibilities. What should we do first? Fly a kite? Play frisbee? Go for a hike?" Her eyes sparkled. I will close my lips fully after this sentence. This is the last sentence I will read and then I will stand still to record my listening segment with minimal head and body movement as if I am listening to someone share a story.
2

1 Minute of Silence

  • Sit still with a relaxed, attentive posture.
  • Keep lips gently closed the entire time.
  • Slight, natural head movements (like you’re listening on a Zoom call).
Replica training typically takes 4–5 hours. You can track the training progress by:

​
High-Quality Training Example

​
Full Body Replica

To create a full body replica for video generation or Lip-sync video, follow these guidelines to ensure optimal quality:

​
Framing & Orientation

  • The subject must be captured from head to toe, with no extra space above or below.
  • Record in vertical format (portrait mode) or crop appropriately to maintain vertical framing.

​
Posture & Movement

  • Remain standing still throughout the recording.
  • Avoid hand gestures or exaggerated body movements to maintain consistency and model quality.

​
Resolution & Quality

  • A 4K resolution is recommended for best results.
  • Ensure consistent lighting, with no shadows or sudden changes in exposure.