Skip to main content
InfiniteTalk is an audio-driven video generation model that creates talking or singing videos from a single image and audio input. It animates faces and bodies to match the audio, making it ideal for creating talking head videos, virtual presenters, or lip-synced content.

Try in playground

Test InfiniteTalk in the Runpod Hub playground.

Request

All parameters are passed within the input object in the request body.
string
required
Text description of the desired video.
string
required
URL of the source image to animate.
string
required
URL of the audio file to drive the animation.
string
required
Output video resolution. Valid options: 480p or 720p.
boolean
default:"true"
Enable content safety checking.

Response

string
Unique identifier for the request.
string
Request status. Returns COMPLETED on success, FAILED on error.
integer
Time in milliseconds the request spent in queue before processing began.
integer
Time in milliseconds the model took to generate the video.
string
Identifier of the worker that processed the request.
object
The generation result containing the video URL and cost.
string
URL of the generated video. This URL expires after 7 days.
float
Cost of the generation in USD.
Video URLs expire after 7 days. Download and store generated videos immediately if you need to keep them.

Cost calculation

InfiniteTalk pricing varies by resolution: