Video To Audio
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("mirelo-ai/sfx2.0/video-to-audio", {
input: {
video_url: "https://di3otfzjg1gxa.cloudfront.net/chase.mp4"
},
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("mirelo-ai/sfx2.0/video-to-audio", {
input: {
video_url: "https://di3otfzjg1gxa.cloudfront.net/chase.mp4"
},
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("mirelo-ai/sfx2.0/video-to-audio", {
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("mirelo-ai/sfx2.0/video-to-audio", {
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.
video_url string* requiredVideo to add sound to: an http(s) URL, or a base64 data URI up to 8 MB.
text_prompt stringOptional text guiding the soundtrack. Name sounds the picture does not show, such as off-screen sounds or an ambience bed, to have them worked into it.
negative_prompt stringSounds to keep out of the result, as a short comma-separated list.
preserve_speech booleanKeep the speech in the input's audio and generate the rest of the soundtrack around it. False generates sound effects only and suppresses speech. Default value: true
duration floatSeconds of sound to generate, from 1 s to 600 s, clamped to the video's length. Over 10 s generates in 10 s windows. A video shorter than 1 s answers 400. Default value: 10
num_samples integerNumber of variations to generate. Billed per sample. Default value: 2
seed integerSeed for generation. -1 or None for random.
upload_audio_format AudioFormatEnumAudio format of each file Default value: "wav"
Possible enum values: wav, mp3, aac, flac
upload_audio_bitrate_kbps integerBitrate in kbps for an mp3 or aac upload. mp3 is written at exactly this constant rate, one of 32, 40, 48, 56, 64, 80, 96, 112, 128, 160, 192, 224, 256, 320. aac takes 32 to 256 as a target the encoder may undershoot on mono or sparse audio. Unset keeps the default: mp3 at LAME V0 VBR, aac at a 256 kbps target. Refused with a lossless upload_audio_format.
return_speech booleanAlso return the input's separated speech as its own audio file, in the response's speech. With preserve_speech false the soundtracks are sound effects only and the speech is separated while they generate. With preserve_speech true it is the speech separated from the input that the soundtracks were generated around, not the speech in them: the model renders that speech anew, so the file does not cancel or double it cleanly when layered onto a soundtrack. The file is mono, in upload_audio_format, and as long as the soundtracks. It is not billed.
{
"video_url": "https://di3otfzjg1gxa.cloudfront.net/chase.mp4",
"text_prompt": "Distant police sirens, tires screeching on asphalt",
"negative_prompt": "music, crowd noise",
"preserve_speech": true,
"duration": 10,
"num_samples": 2,
"upload_audio_format": "wav"
}model string* requiredThe SFX model release that made the output
Each generated soundtrack as an audio file, without the video
The input's separated speech; null unless return_speech
{
"model": "sfx-2.0",
"audio": [
{
"file_name": "generated_audio_1.wav",
"content_type": "audio/wav",
"url": "https://di3otfzjg1gxa.cloudfront.net/chase_output_1.wav"
}
]
}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.
outcome OutcomeEnum* requiredspeech when audio holds the file, no_speech when no window of the input has speech (or it has no audio), failed when separating a window or building the file failed. The soundtracks come back either way.
Possible enum values: speech, no_speech, failed
windows integer* requiredWindows the input was separated in
windows_with_speech integer* requiredWindows that held speech
windows_failed integer* requiredWindows whose separation failed, or whose stem could not be read
The separated speech as one audio file; null unless the outcome is speech