sync/lipsync-2

Generate realistic lipsyncs with Sync Labs' 2.0 model

Capabilities

No capability data available

Community model (estimated from hardware time)

Name	Type	Description	Default	Constraints
`audio`*	string(uri)	Input audio file (.wav)	`—`	—
`video`*	string(uri)	Input video file (.mp4)	`—`	—
`active_speaker`	boolean	Whether to detect active speaker (i.e. whoever is speaking in the clip will be used for lipsync)	`false`	—
`sync_mode`	string	Lipsync mode when audio and video durations are out of sync	`"loop"`	loopbouncecut_offsilenceremap
`temperature`	number	How expressive lipsync can be (0-1)	`0.5`	min: 0, max: 1

audiorequiredstring

Input audio file (.wav)

videorequiredstring

Input video file (.mp4)

active_speakerboolean

Whether to detect active speaker (i.e. whoever is speaking in the clip will be used for lipsync)

Default: false

sync_modestring

Lipsync mode when audio and video durations are out of sync

Default: "loop"

loopbouncecut_offsilenceremap

temperaturenumber

How expressive lipsync can be (0-1)

Default: 0.5min: 0, max: 1

Version: 4f8dc3cfda4fUpdated: 7/25/202640.3K runs