Add a portrait
Choose, drop or paste a photo of one face looking at the camera.
Add a portrait and a voice recording, and AI moves the mouth in time with the words.
Use a voice note, a narration or a dubbed line of up to 30 seconds, and download the MP4 with your audio.
A clear photo of one face looking at the camera, with the mouth visible.
JPG, PNG, WebP, AVIF or HEIC up to 30 MB. You can also paste a photo.Want head movement and longer videos?This free tool moves the mouth of one photo for up to 30 seconds. The Avatar Generator on WaveSpeed AI turns a photo and audio into longer talking or singing videos with natural head and face movement, lip-syncs existing videos too, and has an API.
Open Avatar GeneratorAI-made portraits with a short voice clip, no real people. Choose one and make it talk.
Choose, drop or paste a photo of one face looking at the camera.
Choose the audio file, or a video whose sound the mouth should follow, up to 30 seconds.
Make the video, check the lip sync and download it as an MP4 with your audio.
Create portraits, characters and videos from a short prompt with WaveSpeed AI.
Create a portrait or a character to make talk.
Turn a photo into a short video clip with natural motion.
Turn a picture into a 3D model.
$1 in free credits for eligible new accounts. No card needed. Generators have separate account and credit requirements. The talking photo maker is free.
Open a portrait, add the voice recording and press Make it talk. AI redraws the mouth for every frame to match the sound, and you get an MP4 with your original audio.
Yes: your own recording, a voice note, a narration or a voice made with Text to Speech. Clear speech without music or loud noise gives the best sync.
No. It syncs a still photo: only the mouth area moves, while the head and the rest of the photo stay still. To lip sync an existing video, use the Avatar Generator on WaveSpeed AI.
The mouth follows the sound closely, but it is redrawn at a low resolution, so it can look softer than the rest of the photo. Detailed mode sharpens it; it needs a graphics card and takes longer.
No. Your photo and audio stay on your device, and the AI runs in your browser. The first time, the AI models are downloaded once and kept for next time.
Mouth synced to your audio · Up to 30 seconds · Free, no upload