SyncTalkingImageNode - ComfyUI Built-in Node Documentation

Animate a still portrait into a talking video driven by speech audio, using sync.so’s sync-3 model. The output duration matches the audio duration, and cost scales with output duration.

Inputs

Parameter	Description	Data Type	Required	Range
`image`	A single image with a clearly visible face, up to 4K (4096x2160).	IMAGE	Yes	Exactly one image required
`audio`	Speech audio driving the talking video; the output duration matches it. Chain any TTS node here to drive the animation from text.	AUDIO	Yes	Maximum duration: 600 seconds
`prompt`	Optional guidance for how the portrait comes to life, e.g. ‘make the subject smile and look at the camera’. Leave empty for natural talking motion. (default: "")	STRING	No	Multiline text
`seed`	Seed controls whether the node should re-run; results are non-deterministic regardless of seed. (default: 0)	INT	No	0 to 2147483647
`model`	sync.so generation model. Image input is exclusive to sync-3.	COMBO	Yes	`"sync-3"`
`speaker_selection`	Which face to animate when several people are visible. `default`: let the model decide. `coordinates`: target the face at pixel (speaker_x, speaker_y) in the image. Auto-detection is not supported for images. (default: “default”)	COMBO	No	`"default"` `"coordinates"`
`speaker_x`	X pixel coordinate of the speaker’s face. Only used when speaker_selection is ‘coordinates’. (default: 0)	INT	No	0 to 4096
`speaker_y`	Y pixel coordinate of the speaker’s face. Only used when speaker_selection is ‘coordinates’. (default: 0)	INT	No	0 to 4096
`auto_downscale`	Automatically downscale the image if it exceeds the 4K (4096x2160) input limit; speaker coordinates are scaled to match. When disabled, an oversized image raises an error instead. (default: True)	BOOLEAN	No	True False

Note: The speaker_x and speaker_y parameters are only used when speaker_selection is set to "coordinates". When auto_downscale is enabled, speaker coordinates are automatically scaled to match the downscaled image dimensions.

Outputs

Output Name	Description	Data Type
`video`	The generated talking video with the animated portrait synchronized to the input audio.	VIDEO

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

Source fingerprint (SHA-256): 21f722cdcc5ff017949887ed2252854feebb9b913034dc6a6c3ce196ad089468

​Inputs

​Outputs

Inputs

Outputs