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

Infinitalk Multi API

Video·InfiniteTalk·by infinitetalk

InfiniTalk Multi Video-to-Video transforms multi-speaker footage into naturally dubbed video, syncing each person's lips and expressions to their audio track.

Try it now →
API reference
Runtime (p50)
1m
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-video-to-video",
    "version": "0.0.1",
    "input": {
        "order": "left_right",
        "video": "https://cdn-us.eachlabs.ai/defaults/b43adddaf64e40879bebfe645944c314.mp4",
        "left_audio": "https://cdn-us.eachlabs.ai/uploads/c879a98f-2623-411b-9477-0079a9f7e441.mp3",
        "resolution": "480p",
        "right_audio": "https://cdn-us.eachlabs.ai/uploads/8e58a227-a1f3-4eed-be15-02c5758ed5b6.mp3"
    },
    "webhook_url": ""
}' \
  https://api.eachlabs.ai/v1/prediction/

Related models

4 models
PixVerse Lip Sync v2 AI model preview
PixVerse Lip Sync v2Pixverse
PixVerse Restyle AI model preview
PixVerse RestylePixverse
PixVerse Mimic AI model preview
PixVerse MimicPixverse
VEED Lipsync V2 AI model preview
VEED Lipsync V2VEED
* FAQ

About Infinitalk Multi API

01 / 03

What is InfiniTalk Multi Video-to-Video?

InfiniTalk Multi Video-to-Video is an AI video model that replaces or re-syncs the speech of multiple people in an existing video. Each speaker's lip movements and facial expressions follow their own audio track, so the whole scene stays natural even when several people talk in the same shot