All Models
Sync Lipsync 3
Sync Lipsync 3 matches lip motion in a video to supplied audio, without a per-identity training step.
Call the API endpoint to get the latest, detailed pricing and pricing estimates.
Call the API endpoint to get the latest, detailed pricing and pricing estimates.
Call the API endpoint to get the latest, detailed pricing and pricing estimates.
Sync Lipsync 3
Sync Lipsync 3 is from Sync.so. You give it a video and an audio track, and it matches the mouth in the footage to the new voice. There is no per-identity training step.
It does not generate a face from a still and it does not generate the audio. When the take lengths disagree, sync mode is bounce, loop, cut_off, silence, or remap. The default is cut_off, which trims to the shorter input. Loop and bounce extend the picture to cover longer audio. Silence pads. Remap stretches.
What it's good for
Dubbing, VO replacement, and language versions of an existing talking head. A course that needs several languages, a line legal rewrote in a finished spot, a voiceover recorded badly when you cannot bring the presenter back. Picture and voice both have to already exist.
Model ID
sync/lipsync-3
Output Type
Video
Pricing
$0.135/s
Provider
Sync
Hosting
Protoface
Sync Lipsync 3
Sync Lipsync 3 is from Sync.so. You give it a video and an audio track, and it matches the mouth in the footage to the new voice. There is no per-identity training step.
It does not generate a face from a still and it does not generate the audio. When the take lengths disagree, sync mode is bounce, loop, cut_off, silence, or remap. The default is cut_off, which trims to the shorter input. Loop and bounce extend the picture to cover longer audio. Silence pads. Remap stretches.
What it's good for
Dubbing, VO replacement, and language versions of an existing talking head. A course that needs several languages, a line legal rewrote in a finished spot, a voiceover recorded badly when you cannot bring the presenter back. Picture and voice both have to already exist.