New in AI Video - Lipsync Makes Any Photo Speak

New in AI Video - Lipsync Makes Any Photo Speak

A single headshot is enough to make a presenter. Lipsync matches mouth movement to any script or recording you give it.

What's New

• One clear photo is the whole setup: No filming, no studio and no second take. Upload a headshot of your speaker and you have your presenter.
• Type a script or bring your own audio: Write what they should say and it is voiced for you, or upload a recording you already have and keep the voice you know.
• Runs on Seedance 2.5: Lipsync defaults to the engine that takes an uploaded audio track directly, which is what keeps the sync tight at 1080p.

Lipsync is live now in AI Video.

👉 Try Lipsync now!