Click or drag a file to this area to upload
Format: mp3/wav/m4a, Size: up to 500MB
Duration: 3 seconds to 10 minutes
Image/Video
AI avatar video
Turn a script or recording into a presenter video with a reusable digital avatar. Lip sync is part of the result, while avatar selection, speech, layout, background, and captions make up the full workflow.
It is a generated video in which a selected digital avatar presents text or uploaded speech with synchronized mouth movement.
Lip sync is one part of the workflow. The page also lets you choose a reusable avatar, create speech, set a background and aspect ratio, and add captions.
Yes. You can select an avatar previously trained from an authorized photo or video, subject to the options available for your account.
Yes. The audio workflow supports prerecorded speech, while the text workflow generates speech from a selected voice.
Read the full server-rendered API documentation, or open the interactive API Explorer for all endpoints.