Video model · VEED ·
VEED Lipsync 2 is a video model by VEED. In Endless it costs 221 credits per video and is available on every plan.
VEED Lipsync 2 from VEED rewrites the mouth and lower face of a filmed speaker so they match a new audio track, with no training per face.
VEED Lipsync 2 takes a video and a separate audio file and re-renders the speaker's mouth and lower face to fit the new track. It carries emotion and timing over from the audio, keeps the source resolution, and works zero-shot, so there is no reference footage or fine-tuning per person. It holds up when a hand crosses the face, in low light and with fast camera moves.
Teams use it to ship one shoot in several languages by pairing the original footage with translated voiceovers, to fix a fluffed line without a reshoot, and to update a product name in an existing ad. It also works on animated and non-human characters. It performs best on speakers facing the camera; side angles are supported up to a medium close-up.
In the Endless catalog, VEED Lipsync 2 expects one active speaker per scene. For shots with several people talking, Sync 3 identifies who is speaking. You can try both on the same clip in chat or on the canvas, since they share your workspace credits.
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
by Black Forest Labs
Clips up to 20 seconds with sound, from a prompt, frames or a clip
From 90 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.