sync/react-1

Realistic lipsync with refined human emotion capabilities

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)	`—`	—
`emotion`	string	Emotion prompt for the generation (single word emotions only)	`"neutral"`	happy sad angry disgusted surprised neutral
`model_mode`	string	Edit region for the model (lips/face/head). When head is selected, model generates natural talking head movements along with emotions + lipsync	`"face"`	lips face head
`sync_mode`	string	Lipsync mode when audio and video durations are out of sync	`"loop"`	loop bounce cut_off silence remap
`temperature`	number	How expressive lipsync can be (0-1)	`0.5`	min: 0, max: 1

audio required string

Input audio file (.wav)

video required string

Input video file (.mp4)

emotion string

Emotion prompt for the generation (single word emotions only)

Default: "neutral"

happy sad angry disgusted surprised neutral

model_mode string

Edit region for the model (lips/face/head). When head is selected, model generates natural talking head movements along with emotions + lipsync

Default: "face"

lips face head

sync_mode string

Lipsync mode when audio and video durations are out of sync

Default: "loop"

loop bounce cut_off silence remap

temperature number

How expressive lipsync can be (0-1)

Default: 0.5 min: 0, max: 1

Version: c44d8de5ebd9 Updated: 6/26/2026 975 runs