cinemasetfree.com
← Back to all generators
heygen/lipsync-precision
OfficialView on Replicate →
High-accuracy lip-sync: replace or dub audio on any video with avatar-inference lip sync
Capabilities
No capability data available
Cost
Community model (estimated from hardware time)
Input Parameters
| Name | Type | Description | Default | Constraints |
|---|---|---|---|---|
audio* | string(uri) | Replacement audio file. The video's lip movements will be re-animated to match this audio using high-accuracy avatar inference. | — | — |
video* | string(uri) | Source video file to lip-sync. | — | — |
disable_music_track | boolean | Strip background music from the source video. | false | — |
enable_dynamic_duration | boolean | Allow the output duration to adjust to match the new audio length. | true | — |
enable_speech_enhancement | boolean | Enhance speech quality in the output. | false | — |
audiorequiredstringReplacement audio file. The video's lip movements will be re-animated to match this audio using high-accuracy avatar inference.
videorequiredstringSource video file to lip-sync.
disable_music_trackbooleanStrip background music from the source video.
Default:
falseenable_dynamic_durationbooleanAllow the output duration to adjust to match the new audio length.
Default:
trueenable_speech_enhancementbooleanEnhance speech quality in the output.
Default:
falseVersion:
03d0f07dd626Updated: 7/25/20261.5K runs