Try H3 Max Director
Log-inSign-up
Contact SalesLog-inSign-up

Minimax logo
minimax/h3-max/lip-sync/image-to-video

H3 Max Lip Sync generates a video from an image and supplied audio, synchronizing mouth movements to the soundtrack. It supports optional transcription guidance and output resolutions from 480p to 2K.
Learn more about H3
Inference
Commercial use
Schema
LLMs
PlaygroundAPIExamples

Table of contents

About

Lip Sync Image To Video

1. Calling the API#

Install the client#

The client provides a convenient way to interact with the model API.

npm install --save @fal-ai/client

Setup your API Key#

Set FAL_KEY as an environment variable in your runtime.

export FAL_KEY="YOUR_API_KEY"

Submit a request#

The client API handles the API submit protocol. It will handle the request status updates and return the result when the request is completed.

import { fal } from "@fal-ai/client";

const result = await fal.subscribe("minimax/h3-max/lip-sync/image-to-video", {
  input: {
    image_url: "",
    audio_url: ""
  },
  logs: true,
  onQueueUpdate: (update) => {
    if (update.status === "IN_PROGRESS") {
      update.logs.map((log) => log.message).forEach(console.log);
    }
  },
});
console.log(result.data);
console.log(result.requestId);

2. Authentication#

The API uses an API Key for authentication. It is recommended you set the FAL_KEY environment variable in your runtime when possible.

API Key#

In an environment where you cannot set environment variables, you can configure the API key manually on the client.
import { fal } from "@fal-ai/client";

fal.config({
  credentials: "YOUR_FAL_KEY"
});

3. Queue#

Submit a request#

The client API provides a convenient way to submit requests to the model.

import { fal } from "@fal-ai/client";

const { request_id } = await fal.queue.submit("minimax/h3-max/lip-sync/image-to-video", {
  input: {
    image_url: "",
    audio_url: ""
  },
  webhookUrl: "https://optional.webhook.url/for/results",
});

Fetch request status#

You can fetch the status of a request to check if it is completed or still in progress.

import { fal } from "@fal-ai/client";

const status = await fal.queue.status("minimax/h3-max/lip-sync/image-to-video", {
  requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b",
  logs: true,
});

Get the result#

Once the request is completed, you can fetch the result. See the Output Schema for the expected result format.

import { fal } from "@fal-ai/client";

const result = await fal.queue.result("minimax/h3-max/lip-sync/image-to-video", {
  requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b"
});
console.log(result.data);
console.log(result.requestId);

4. Files#

Some attributes in the API accept file URLs as input. Whenever that's the case you can pass your own URL or a Base64 data URI.

Data URI (base64)#

You can pass a Base64 data URI as a file input. The API will handle the file decoding for you. Keep in mind that for large files, this alternative although convenient can impact the request performance.

Hosted files (URL)#

You can also pass your own URLs as long as they are publicly accessible. Be aware that some hosts might block cross-site requests, rate-limit, or consider the request as a bot.

Uploading files#

We provide a convenient file storage that allows you to upload files and use them in your requests. You can upload files using the client API and use the returned URL in your requests.

import { fal } from "@fal-ai/client";

const file = new File(["Hello, World!"], "hello.txt", { type: "text/plain" });
const url = await fal.storage.upload(file);

Read more about file handling in our file upload guide.

5. Schema#

Input#

image_url string* required

Image to animate. The aspect ratio must be between 0.4 and 2.5.

audio_url string* required

Audio to synchronize the mouth movements to, at least 5 seconds long. Audio over 15 seconds is automatically clipped to its first 15 seconds. The output video matches the clipped audio duration in a single generation.

resolution ResolutionEnum

Output resolution. Uses the supported aspect ratio nearest the image. Default value: "768P"

Possible enum values: 480P, 768P, 1080P, 2K

enable_transcription boolean

Transcribe the supplied audio to guide lip synchronization. When disabled, synchronize to the audio without a transcript. Default value: true

seed integer

Random seed; selected randomly if omitted.

enable_safety_checker boolean

Enable content safety checks. Default value: true

{
  "image_url": "",
  "audio_url": "",
  "resolution": "768P",
  "enable_transcription": true,
  "enable_safety_checker": true
}

Output#

video File* required

Lip-synced video with the supplied soundtrack.

seed integer* required

Random seed used for generation.

duration float* required

Output duration in seconds.

{
  "video": {
    "url": "",
    "content_type": "image/png",
    "file_name": "z9RV14K95DvU.png",
    "file_size": 4404019
  }
}

Other types#

TranscriptSegment#

start float* required

Speech start in source-video seconds.

end float* required

Speech end in source-video seconds.

text string* required

Source text, or final dialogue when auto_translate is false.

File#

url string* required

The URL where the file can be downloaded from.

content_type string

The mime type of the file.

file_name string

The name of the file. It will be auto-generated if not provided.

file_size integer

The size of the file in bytes.

DubbingSegment#

start float* required
end float* required
text string* required
translated_text string* required

AVCheckpoint#

url string* required

Unguesseable service-issued checkpoint artifact URL.

sha256 string* required
size_bytes integer* required
version integer

Default value: 1

model string

Default value: "minimax-h3"

transformer_family TransformerFamilyEnum

Default value: "fl2va"

Possible enum values: fl2va, ref2va, ref2va-tdm-k10

loras list<CheckpointLoRA>
resolution ResolutionEnum* required

Possible enum values: 480p, 544p, 640p, 704p, 768p, 1080p, 1440p

checkpoint_id string* required
owner_id string* required

sha256 of the issuing caller's gateway identity.

source_request_id string* required

Issuing request id — audit/provenance lineage only.

issued_at integer* required
expires_at integer* required
audience string

Default value: "minimax-h3/continue-video"

signature string* required

Service HMAC binding the complete descriptor.

CheckpointLoRA#

locator string* required

Opaque service-owned adapter locator.

sha256 string* required
size_bytes integer* required
scale float* required
transformer_family TransformerFamilyEnum* required

Possible enum values: fl2va, ref2va, ref2va-tdm-k10

transformer_variant string* required

H3MaxCameraKeyframe#

time float* required

Normalized video time, from 0 at the start to 1 at the end.

azimuth float* required

Horizontal camera angle around the subject, in degrees.

elevation float* required

Vertical camera angle around the subject, in degrees.

distance float* required

Camera distance from the subject in normalized scene units.

Related Models