OpenWeights · Infinitetalk Fast · digital human
Infinitetalk Fast · Video to Video Multi
Render Infinitetalk Fast through the same job workflow as Seedance — from $0.101 per render.
What it renders
InfiniteTalk fast video-to-video multi converts a video and two audio inputs into multi-character talking or singing videos. Hand over the model id and your shot settings, keep the job id, and collect the finished clip once the job lands. Pricing is per completed render from $0.101 and is locked in before the first frame is queued.
Motion-first defaults
Infinitetalk Fast · Video to Video Multi opens on workable shot framing before you tune anything.
Async by design
Renders run as background jobs; poll at your own pace instead of holding a connection open.
Clip-ready output
Results arrive as a downloadable asset from private storage with a short-lived link.
Digital Human shots
Digital Human stays available for Infinitetalk Fast · Video to Video Multi without leaving the video workspace.
Infinitetalk Fast shots
Infinitetalk Fast stays available for Infinitetalk Fast · Video to Video Multi without leaving the video workspace.
Video shots
Video stays available for Infinitetalk Fast · Video to Video Multi without leaving the video workspace.
From the shot board
Wire the render pipeline
Grab a key
Sign in, create a server-side key and add a little balance.
Confirm the endpoint
GET /v1/models lists open/infinitetalk-fast/video-to-video-multi with its shot limits and current rate.
Queue the render
POST /v1/jobs with the model id, your shot settings and a unique Idempotency-Key.
Collect the clip
Poll GET /v1/jobs/{id} until it lands, then fetch GET /v1/jobs/{id}/content.
Queue the render
# Seedance API — queue one render
curl https://seedanceapi.pro/v1/jobs \
-H "Authorization: Bearer $SEEDANCE_API_KEY" \
-H "Idempotency-Key: $REQUEST_ID" \
-H "Content-Type: application/json" \
-d '{"model":"open/infinitetalk-fast/video-to-video-multi","order":"meanwhile","prompt":"A slow dolly across a rain-lit neon street, shallow depth of field.","seed":1}'Shot settings
- left_audioneeded
- string
- orderoptional
- string · meanwhile / left_right / right_left
- promptoptional
- string
- right_audioneeded
- string
- seedoptional
- integer
- videoneeded
- string
Try a render from here
This queues a real job on this site's /v1/jobs using your signed-in balance, or an API key if you are not signed in. A pasted key lives only in this tab; the render is billed at the quoted USD rate.
Or sign in to use your account balance.
Before you wire it in
How do I start a Infinitetalk Fast · Video to Video Multi render?
Authenticate, check the live model list for open/infinitetalk-fast/video-to-video-multi, then POST the model id and shot settings to /v1/jobs with an Idempotency-Key. Poll the job id until it settles, then download the clip.
What can I control on Infinitetalk Fast · Video to Video Multi?
Infinitetalk Fast · Video to Video Multi accepts left_audio, order, prompt, right_audio, seed, video. Unknown keys are rejected before the render is queued, so a typo never burns a job.
What does a Infinitetalk Fast · Video to Video Multi render cost?
Pricing is per render and starts at $0.101. The exact figure for your settings is returned by the model list and reserved before the job is accepted.
Is the same Seedance key valid for Infinitetalk Fast · Video to Video Multi?
Yes — Infinitetalk Fast · Video to Video Multi runs on the same account, key and wallet as Seedance. Each endpoint is enabled individually, so verify the route before you depend on it.
Why does my Infinitetalk Fast · Video to Video Multi job show as queued?
Video rendering is asynchronous: queued and running are normal. Keep polling until the job succeeds, fails or asks for review, and never resubmit the same Idempotency-Key expecting a second render.