Lip Sync animates a static portrait photo to match a provided audio clip, producing a photorealistic talking-head video — no camera required.

How to use Lip Sync

1. 1Navigate to Create → Lip Sync in the sidebar.
2. 2Upload a person photo: choose a saved avatar from your Avatars library, or upload a new image (JPG, PNG, WEBP, max 4 MB). The photo should show a clear, forward-facing face.
3. 3Upload an audio file (MP3 or WAV, max 4 MB). The audio must be 35 seconds or shorter.
4. 4The page automatically detects the audio duration and shows the credit cost (duration in seconds × 6).
5. 5Optionally add a Style Prompt — a short description to guide the generation style (e.g. "a person speaking naturally with subtle expressions").
6. 6If your audio is longer than 35 seconds, trim it before uploading — the platform enforces a hard 35-second cap.
7. 7Click Generate. The job is queued and typically completes in 30–90 seconds.
8. 8The output video appears in the results panel and is saved to your Library.

Credit cost example

Tips

• Use a clean, well-lit headshot with a neutral expression for the most natural results
• Avoid photos with heavy shadows across the face or extreme angles
• Generate voiceover using the Audio Studio tool, download it, then upload it here
• Keep clips concise — 5–15 seconds works best for short-form social content
• The style prompt is optional but can improve expressiveness — try "speaking naturally with subtle facial expressions"