Can I make a still photo talk?

Yes. Upload a single clear portrait instead of a video and the app animates it into a talking avatar synced to your audio. For dubbing existing footage, upload a video instead.

Do I have to upload an audio file?

No — you can type a script and the app generates the voice for you with text-to-speech. If you upload your own audio file, that’s used directly and no speech is synthesized.

What audio formats are supported?

MP3, WAV, and M4A files up to 15 MB. Keep the clip short and clear for the best sync.

Should I upload a video or a photo?

Upload a video when you want to re-sync or dub existing footage. Upload a photo when you want to animate a still portrait into a talking video. Provide one or the other.

How is text-to-speech billed?

The base cost is the lip-sync video generation, shown before you run. If you type a script instead of uploading audio, a small text-to-speech charge (priced per 1,000 characters) is added on top.

Do I need an account?

Yes — lip sync runs a premium video model, so it needs a free account. You start with 200 credits and always pay the wholesale rate.

Apps100 credits · 50¢ per run

Lip-sync a video or make a photo talk

Add a voice track or type a script — the mouth moves to match, perfectly.

Video to re-sync (option A)(optional)

Photo to animate (option B)(optional)

Voice track (optional)(optional)

Result

Your result appears here

Add a video or a photo

Upload a talking-head video to re-sync, or a single portrait photo to turn into a talking avatar.

Provide the voice

Upload an audio file, or type a script and let built-in text-to-speech create the voice.

Generate and download

The model syncs the mouth to the audio. Watch it play, then download the MP4.

Lip-sync a video or make a photo talk

Add a video or a photo

Provide the voice

Generate and download

Everything useful, nothing to study first.

Quick answers

Related apps

Motion Control

Character Swap

Image to Video

Start creating today