MiniMax H3 Max Lip Sync
MiniMax · Video · Image → Video
MiniMax H3 Max lip-synced video from a portrait and an audio track — mouth movements follow the soundtrack, optionally guided by a transcript. 5-14.8s of audio, up to 2K.
Model ID:
minimax-h3-max-lip-syncWorkflow: minimax/h3-max/lip-sync/image-to-videoLip SyncImage InputAudio Input2K5-15 sec
Install the SDK
The SDK targets Node 20+ and ships with TypeScript types.
npm
npm install @picsart/ai-sdkAuthenticate
Create a client once with your API key — it's sent as a bearer token on every request.
TypeScript
import { createClient } from '@picsart/ai-sdk';
const ai = createClient({
apiKey: process.env.PICSART_API_KEY, // sent as: Authorization: Bearer <key>
apiUrl: 'https://api.green-salad-4efd.toolsminati.workers.dev',
});Run the model
Call the model with its parameters. This example uses the required ones.
TypeScript
import { createClient } from '@picsart/ai-sdk';
const ai = createClient({
apiKey: process.env.PICSART_API_KEY,
apiUrl: 'https://api.green-salad-4efd.toolsminati.workers.dev',
});
const result = await ai.generate('minimax-h3-max-lip-sync', {
startFrame: "https://cdn.example.com/input.jpg",
audioUrl: "https://cdn.example.com/input.mp3",
resolution: "768p"
});
console.log(result.url); // video URLParameters
6 parameters. Required ones must be supplied; the rest fall back to their defaults. The API takes these same names over HTTP.
| Parameter | Type | Required | Default | Details |
|---|---|---|---|---|
startFramePortrait Image | file (image) | yes | — | — |
audioUrlAudio Track | file (audio) | yes | — | — |
resolution | enum | no | 768p | 480p, 768p, 1080p, 2k |
enableTranscriptionTranscription | boolean | no | false | — |
seed | range | no | -1 | -1–2147483647 |
enableSafetyCheckerSafety Checker | boolean | no | true | — |
Output
generate() resolves once the job completes. A video URL.
Result
{
"items": [
{
"url": "https://cdn.green-salad-4efd.toolsminati.workers.dev/…/result"
}
],
"model": "minimax-h3-max-lip-sync"
}