Infinitetalk Video To Video Multi

Playground

InfiniteTalk Video-to-Video Multi converts a video and two audio inputs into multi-character talking or singing videos at up to 720p. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

InfiniteTalk Video-to-Video Multi

What is InfiniteTalk Video-to-Video Multi?

InfiniteTalk Video-to-Video Multi creates videos with accurate lip sync for multiple characters by combining an input video and two audio tracks (left and right). It maintains identity across unlimited-length videos, ensuring precise lip synchronization while matching head, face, and body movements to each audio source.

Why it looks great

Accurate lip synchronization: aligns lip motion precisely with audio for both characters, preserving natural rhythm and pronunciation.
Full-body coherence: captures head movements, facial expressions, and posture changes beyond the lips.
Identity preservation: maintains consistent facial identity and visual style across frames.
Video-to-video capability: uses an existing video as the base, preserving the original scene and motion.
Mask control: optional mask images let you define which regions can move.
Instruction following: accepts text prompts to control scene, pose, or behavior while syncing to audio.

Pricing

Output Resolution	Cost per 5 seconds	Max Length
480p	$0.15	10 minutes
720p	$0.30	10 minutes

Billing Rules

Standard Rate: $0.03 per second
HD (720p) Rate: $0.06 per second (Double the Standard Rate)
Minimum Charge: All videos are billed for a minimum of 5 seconds (costing at least $0.15).
Billing Cap: To keep your costs predictable, billing is capped at 600 seconds (10 minutes).

How to Use

Upload the left and right audio files.
Upload your video (The video should clearly show two people).
(Optional) Upload a mask image to control which regions can move.
Select the speaking order (left to right, right to left, or meanwhile).
Select the resolution (480p or 720p).
Write the prompt if needed.
Submit the job and download the results once they’re ready.

Note

Max clip length per job: up to 10 minutes
Processing speed: approximately 10–30 seconds of wall time per 1 second of video (varies by resolution and queue load)
Mask safety tip: Do not upload the full image as mask_image. The mask should only cover the regions you want to animate—otherwise the result may render as fully black.

More Versions

Reference

Build your own digital human

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result


# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/infinitetalk/video-to-video-multi" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "order": "meanwhile",
    "resolution": "480p",
    "seed": -1
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"

Parameters

Task Submission Parameters

Request Parameters

Parameter	Type	Required	Default	Range	Description
video	string	Yes		-	The video for generating the output.
left_audio	string	Yes	-	-	The audio of the persion on the left for generating the output.
right_audio	string	Yes	-	-	The audio of the persion on the right for generating the output.
mask_image	string	No		-	Optional mask image to specify the person in the video to animate.
prompt	string	No		-	The positive prompt for the generation.
order	string	No	meanwhile	meanwhile, left_right, right_left	The order of the two audio sources in the output video, "meanwhile" means both audio sources will play at the same time, "left_right" means the left audio will play first then the right audio will play, "right_left" means the right audio will play first then the left audio will play.
resolution	string	No	480p	480p, 720p	The resolution of the output video.
seed	integer	No	-1	-1 ~ 2147483647	The random seed to use for the generation. -1 means a random seed will be used.

Response Parameters

Parameter	Type	Description
code	integer	HTTP status code (e.g., 200 for success)
message	string	Status message (e.g., “success”)
data.id	string	Unique identifier for the prediction, Task Id
data.model	string	Model ID used for the prediction
data.outputs	array	Array of URLs to the generated content (empty when status is not `completed`)
data.urls	object	Object containing related API endpoints
data.urls.get	string	URL to retrieve the prediction result
data.has_nsfw_contents	array	Array of boolean values indicating NSFW detection for each output
data.status	string	Status of the task: `created`, `processing`, `completed`, or `failed`
data.created_at	string	ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.error	string	Error message (empty if no error occurred)
data.timings	object	Object containing timing details
data.timings.inference	integer	Inference time in milliseconds

Result Request Parameters

Parameter	Type	Required	Default	Description
id	string	Yes	-	Task ID

Result Response Parameters

Parameter	Type	Description
code	integer	HTTP status code (e.g., 200 for success)
message	string	Status message (e.g., “success”)
data	object	The prediction data object containing all details
data.id	string	Unique identifier for the prediction, the ID of the prediction to get
data.model	string	Model ID used for the prediction
data.outputs	string	Array of URLs to the generated content (empty when status is not completed).
data.urls	object	Object containing related API endpoints
data.urls.get	string	URL to retrieve the prediction result
data.status	string	Status of the task: `created`, `processing`, `completed`, or `failed`
data.created_at	string	ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.error	string	Error message (empty if no error occurred)
data.timings	object	Object containing timing details
data.timings.inference	integer	Inference time in milliseconds

Infinitetalk Video To Video Instant Character