Video model · MiniMax ·
MiniMax H3 Max Lip-sync is a video model by MiniMax. In Endless it costs from 189 credits per video and is available on every plan.
MiniMax H3 Max Lip-sync, built on MiniMax H3, animates a single portrait so it speaks your audio track, with output from 480p up to 2K.
MiniMax H3 Max Lip-sync is the lip-sync version of H3 Max, post-trained from MiniMax H3. You give it one image with a visible face and an audio file, and it returns a video of that face speaking the audio with the soundtrack attached. The face can be a photo, a 3D render, a 2D illustration or a painting. By default the audio is transcribed and the transcript guides the mouth shapes, which keeps sync accurate across languages.
Teams use it for spokesperson clips in ads, presenters for training lessons and narrated characters in games and animation. Because it starts from a still, you can give a brand mascot or an illustrated guide a voice without filming anyone. The output follows the nearest supported aspect ratio to your image, so vertical, square and wide portraits all work.
MiniMax H3, also in the Endless catalog, generates whole scenes from a prompt and reference images. Pick H3 Max Lip-sync when you already have the voice and the face and only need them to talk together.
by MiniMax
Clips up to 15 seconds at 2K with native stereo sound
From 84 credits per video
by ByteDance
30-second clips in one pass, guided by up to 50 references
From 51 credits per video
by ByteDance
Clips of 4 to 15 seconds steered by image, video and audio references
From 16 credits per video
Start free, create a project, and bring your brand’s references together. Or book a demo to explore Endless with your team.