Animate a portrait with a speech recording

Prepare the two inputs

Choose a clear portrait and a recording with understandable speech. Use a photo and audio you have permission to use. Start with a front-facing portrait so you can judge the mouth movement clearly.

The Face Image input accepts JPG, JPEG, PNG and WebP. Audio Track accepts MP3, WAV, OGG, M4A and AAC. Follow the size limit shown beside each input.

How to make the talking video

1. Add the portrait and recording

Upload the portrait under Face Image and the speech under Audio Track. Both inputs are needed. If you selected the wrong file, use Remove beside that input and choose another.

2. Check the audio limit and expression

Under Video quality, choose from the options currently available. Each option shows its credit cost and maximum audio length. Trim your recording if it is too long for that option. Expression Style offers natural, expressive and subtle.

3. Generate and review

Click Generate AI Talking Head. Watch the whole clip with sound, checking mouth timing, facial appearance and movement. Use Download to save the MP4 you want to keep.

The animation can change the face

A generated talking video may alter facial details or produce movement that does not match the recording. Treat it as an animation, not a record of the person actually speaking. Review the result before sharing it.