Flint Image 4K is here. Frontier quality, at a fraction of the price.

Infinitalk Multi API

Video·InfiniteTalk·by infinitetalk

InfiniTalk Multi Image-to-Video turns one photo of two or more people into a lip-synced conversation video, with each speaker matched to their own audio track.

Try it now →
API reference
Runtime (p50)
8m
Estimated price
From $0.03
Call the API
prediction.sh
sh
curl -X POST \
  -H "Authorization: Bearer $EACHLABS_API_KEY" \
  -H "Content-Type: application/json" \
  --data '{
    "model": "infinitalk-multi-image-to-video",
    "version": "0.0.1",
    "input": {
        "image": "https://cdn-us.eachlabs.ai/defaults/8220543cc7c3411b92c46796d9bfafc8.png",
        "order": "left_right",
        "left_audio": "https://cdn-us.eachlabs.ai/defaults/3d16e688b5f5415ba1b1c595400a4daf.mp3",
        "resolution": "720p",
        "right_audio": "https://cdn-us.eachlabs.ai/defaults/67bbd343acf8484fbc40fceebbdfaea4.mp3"
    },
    "webhook_url": ""
}' \
  https://api.eachlabs.ai/v1/prediction/

Related models

4 models
Kling o3 4K · Image to Video AI model preview
Kling o3 4K · Image to VideoKling
Google Gemini Omni Flash · Image to Video AI model preview
Google Gemini Omni Flash · Image to VideoGoogle
PixVerse C1 Transition AI model preview
PixVerse C1 TransitionPixverse
P Video Animate AI model preview
P Video AnimatePruna AI
* FAQ

About Infinitalk Multi API

01 / 03

What is InfiniTalk Multi Image-to-Video?

InfiniTalk Multi Image-to-Video is an AI video generation model that animates two or more people from a single photo so they speak in a natural conversation. You provide one image and audio for each speaker, and the model maps every voice to the right person with accurate lip sync and realistic facial expressions.