fal Assets is now live!
Docs
Log-inSign-up

fal-ai/stable-audio-3/small/sfx/audio-inpainting

Stable Audio 3 Small SFX audio inpainting is a 459 million parameter latent diffusion model that fills in or reworks selected segments of a sound-effect track guided by text prompts.
Inference
Commercial use
Schema
LLMs
PlaygroundAPIExamples

Table of contents

About

Ep Small Sfx Inp

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("fal-ai/stable-audio-3/small/sfx/audio-inpainting", {
  input: {
    prompt: "punchy kick drum fill",
    audio_url: "https://storage.googleapis.com/falserverless/model_tests/diffrythm/rock_en.wav",
    mask_start_seconds: 4,
    mask_end_seconds: 8
  },
  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 case your app is running in an environment where you cannot set environment variables, you can set the API Key manually as a client configuration.
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("fal-ai/stable-audio-3/small/sfx/audio-inpainting", {
  input: {
    prompt: "punchy kick drum fill",
    audio_url: "https://storage.googleapis.com/falserverless/model_tests/diffrythm/rock_en.wav",
    mask_start_seconds: 4,
    mask_end_seconds: 8
  },
  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("fal-ai/stable-audio-3/small/sfx/audio-inpainting", {
  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("fal-ai/stable-audio-3/small/sfx/audio-inpainting", {
  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#

negative_prompt string

Text description of qualities to avoid in the output. Default value: ""

num_inference_steps integer

Number of sampling steps. Post-trained (distilled) checkpoints look good with the default 8 and gain little from going higher. Default value: 8

guidance_scale float

Classifier-free guidance scale. Higher values follow the prompt more strictly. Only effective on base (non-distilled) checkpoints. Default value: 1

seed integer

Random seed for reproducible outputs. Omit for a random seed.

enable_prompt_expansion boolean

If True, the prompt will be expanded using an LLM for more detailed and higher quality results.

enable_safety_checker boolean

Enable NSFW content safety checking. Default value: true

sync_mode boolean

If True, the audio is returned inline as a data URI and the result is not saved to the request history.

output_format OutputFormatEnum

Container format for the generated audio output. Default value: "mp3"

Possible enum values: mp3, wav, flac, ogg, opus, m4a, aac

bitrate string

Audio bitrate for compressed output formats (e.g., mp3, aac, opus). Format e.g. '192k' or '320k'. Ignored for lossless formats (wav, flac). Default value: "192k"

prompt string* required

Text description guiding how the masked region is regenerated.

audio_url string* required

Source audio. Only the masked region is regenerated.

mask_start_seconds float* required

Start of the region to regenerate, in seconds.

mask_end_seconds float* required

End of the region to regenerate, in seconds.

{
  "num_inference_steps": 8,
  "guidance_scale": 1,
  "enable_safety_checker": true,
  "output_format": "mp3",
  "bitrate": "192k",
  "prompt": "punchy kick drum fill",
  "audio_url": "https://storage.googleapis.com/falserverless/model_tests/diffrythm/rock_en.wav",
  "mask_start_seconds": 4,
  "mask_end_seconds": 8
}

Output#

audio File* required

The generated audio clip.

seed integer* required

The random seed used for generation.

prompt string* required

The prompt used for generation.

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

Other types#

LoRAWeight#

path string* required

URL or HuggingFace repo id pointing to the LoRA weights.

weight_name string

Name of the LoRA weight file. Used only if path is a HuggingFace repository and required only if the repo contains more than one safetensors file.

scale float

Multiplicative strength applied to the LoRA at inference time. Default value: 1

target TargetEnum

Which sub-module of Stable Audio 3 the LoRA targets. dit applies the LoRA only to the diffusion transformer, conditioner only to the text conditioner, and both to both. Default value: "dit"

Possible enum values: dit, conditioner, both

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.

Related Models