fal-ai/longcat-multi-avatar/image-audio-to-video
Loading API documentation
This model is no longer supported.
This model is no longer supported.
Generate a multi-speaker talking avatar video from an image and two audio files.
Each speaker can have their own audio track, and their lip movements will be synchronized independently based on their bounding box regions.
The client provides a convenient way to interact with the model API.
npm install --save @fal-ai/clientThe @fal-ai/serverless-client package has been deprecated in favor of @fal-ai/client. Install the new package and update your imports — see client setup.
Set FAL_KEY as an environment variable in your runtime.
export FAL_KEY="YOUR_API_KEY"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("fal-ai/longcat-multi-avatar/image-audio-to-video", {
input: {
image_url: "https://raw.githubusercontent.com/meituan-longcat/LongCat-Video/refs/heads/main/assets/avatar/multi/sing.png"
},
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);The API uses an API Key for authentication. It is recommended you set the FAL_KEY environment variable in your runtime when possible.
import { fal } from "@fal-ai/client";
fal.config({
credentials: "YOUR_FAL_KEY"
});When running code on the client-side (e.g. in a browser, mobile app or GUI applications), make sure to not expose your FAL_KEY. Instead, use a server-side proxy to make requests to the API. For more information, check out our server-side integration guide.
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("fal-ai/longcat-multi-avatar/image-audio-to-video", {
input: {
image_url: "https://raw.githubusercontent.com/meituan-longcat/LongCat-Video/refs/heads/main/assets/avatar/multi/sing.png"
},
webhookUrl: "https://optional.webhook.url/for/results",
});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("fal-ai/longcat-multi-avatar/image-audio-to-video", {
requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b",
logs: true,
});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("fal-ai/longcat-multi-avatar/image-audio-to-video", {
requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b"
});
console.log(result.data);
console.log(result.requestId);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.
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.
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.
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);The client will auto-upload the file for you if you pass a binary object (e.g. File, Data).
Read more about file handling in our file upload guide.
image_url string* requiredThe URL of the image containing two speakers.
audio_url_person1 stringThe URL of the audio file for person 1 (left side). Default value: "https://raw.githubusercontent.com/meituan-longcat/LongCat-Video/refs/heads/main/assets/avatar/multi/sing_man.WAV"
audio_url_person2 stringThe URL of the audio file for person 2 (right side). Default value: "https://raw.githubusercontent.com/meituan-longcat/LongCat-Video/refs/heads/main/assets/avatar/multi/sing_woman.WAV"
prompt stringThe prompt to guide the video generation. Default value: "Two people are having a conversation with natural expressions and movements."
negative_prompt stringThe negative prompt to avoid in the video generation. Default value: "Close-up, Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards"
Bounding box for person 1. If not provided, defaults to left half of image.
Bounding box for person 2. If not provided, defaults to right half of image.
audio_type AudioTypeEnumHow to combine the two audio tracks. 'para' (parallel) plays both simultaneously, 'add' (sequential) plays person 1 first then person 2. Default value: "para"
Possible enum values: para, add
num_inference_steps integerThe number of inference steps to use. Default value: 30
text_guidance_scale floatThe text guidance scale for classifier-free guidance. Default value: 4
audio_guidance_scale floatThe audio guidance scale. Higher values may lead to exaggerated mouth movements. Default value: 4
resolution ResolutionEnumResolution of the generated video (480p or 720p). Billing is per video-second (16 frames): 480p is 1 unit per second and 720p is 4 units per second. Default value: "480p"
Possible enum values: 480p, 720p
num_segments integerNumber of video segments to generate. Each segment adds ~5 seconds of video. First segment is ~5.8s, additional segments are 5s each. Default value: 1
seed integerThe seed for the random number generator.
enable_safety_checker booleanWhether to enable safety checker. Default value: true
{
"image_url": "https://raw.githubusercontent.com/meituan-longcat/LongCat-Video/refs/heads/main/assets/avatar/multi/sing.png",
"audio_url_person1": "https://raw.githubusercontent.com/meituan-longcat/LongCat-Video/refs/heads/main/assets/avatar/multi/sing_man.WAV",
"audio_url_person2": "https://raw.githubusercontent.com/meituan-longcat/LongCat-Video/refs/heads/main/assets/avatar/multi/sing_woman.WAV",
"prompt": "Static camera, In a professional recording studio, two people stand facing each other, both wearing large headphones. They are speaking clearly into a large condenser microphone suspended between them. They looked at each other affectionately and occasionally shook their heads according to the rhythm. The soundproofed walls and visible recording equipment create an atmosphere focused on capturing high-quality audio as they interact and communicate.",
"negative_prompt": "Close-up, Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards",
"audio_type": "para",
"num_inference_steps": 30,
"text_guidance_scale": 4,
"audio_guidance_scale": 4,
"resolution": "480p",
"num_segments": 1,
"enable_safety_checker": true
}The generated video file.
seed integer* requiredThe seed used for generation.
{
"video": {
"url": "https://v3b.fal.media/files/b/0a87a882/k7N4EBTQnVM9nCW9ylN8i_output_87614f102ba94cc0b101d058a815c81f.mp4",
"content_type": "video/mp4"
},
"seed": 424911732
}x float* requiredX-coordinate of the top-left corner
y float* requiredY-coordinate of the top-left corner
w float* requiredWidth of the bounding box
h float* requiredHeight of the bounding box
label string* requiredLabel of the bounding box
url string* requiredThe URL where the file can be downloaded from.
content_type stringThe mime type of the file.
file_name stringThe name of the file. It will be auto-generated if not provided.
file_size integerThe size of the file in bytes.