infery
← All models

AI Avatar Multi

ai-avatar-multi

Video editby AI Avatar

MultiTalk model generates a multi-person conversation video from an image and audio files. Creates a realistic scene where multiple people speak in sequence.

Example

Details

Accepts
image + audio

Pricing

Price
25 cr / second

Prices in credits (1 credit = $0.01).

Data schema

Input

FieldTypeDescription
seedintegerRandom seed for reproducibility. If None, a random seed is chosen.
promptrequiredstringThe text prompt to guide video generation.
image_urlrequiredstringURL of the input image. If the input image does not match the chosen aspect ratio, it is resized and center cropped.
num_framesintegerNumber of frames to generate. Must be between 81 to 129 (inclusive). If the number of frames is greater than 81, the video will be generated with 1.25x more billing units.
resolutionstringenum: 480p, 720pResolution of the video to generate. Must be either 480p or 720p.
accelerationstringenum: none, regular, highThe acceleration level to use for generation.
first_audio_urlrequiredstringThe URL of the Person 1 audio file.
second_audio_urlThe URL of the Person 2 audio file.
use_only_first_audiobooleanWhether to use only the first audio file.

Output

FieldTypeDescription
seedintegerThe seed used for generation.
videoThe generated video file.