Upload a portrait and an audio track. The model animates the face so the lips follow the speech or song — the video is as long as the audio.
From 36 credits per result
Upload a portrait and an audio track. The model animates the face so the lips follow the speech or song — the video is as long as the audio.
Keep it simple: one clear action and, if you like, one camera move give the best results.
[expression] + [head movement]A front-facing photo with a visible mouth works best.
Speech or a song in MP3, WAV or M4A, up to 15 seconds — the video length follows the audio.
Optionally describe the expression and head movement in the prompt.
Only upload content you have the rights to. Content involving minors, real people without their consent, or anything illegal is never allowed.
Content PolicyFrom 36 credits per result, depending on the model and settings. The exact price is shown on the Generate button before you run it.
Usually from a few seconds to a couple of minutes, depending on the model, length and resolution.
Open “How it works?” on any tool page. Templates are also a quick way to start with a proven setup.
Credits are refunded to your balance automatically — for failed generations and system errors.
Yes — sign up for free with email or Google, then pay only for what you generate on CensorVid.
Make photos talk with any audio.
Generate lipsync18+ only · Legal content only