fal Sandbox is here - run all your models together! 🏖️
DocsBlogPricingEnterpriseCareersResearch Grants
Log-inSign-up

Sonauto V2 Text to Audio

sonauto/v2/inpaint
Replace sections of an existing audio with newly generated content
Inference
Commercial use
Partner
PlaygroundAPI

About

Replace or regenerate specific sections of an existing song using Sonauto, an AI music model that transforms text into full songs with lyrics. This function allows you to modify parts of a song while keeping the rest intact, perfect for fixing problematic sections or changing specific lyrics.

Unlike generate and extend, inpaint requires both tags AND lyrics. The regenerated section will seamlessly blend with the surrounding audio while incorporating the specified tags and lyrics.

You can view a list of all available tags at https://sonauto.ai/tag-explorer.

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("sonauto/v2/inpaint", {
  input: {
    lyrics_prompt: "[Chorus]
  Pigs are soaring in the sky
  Wings of bacon flying by
  ",
    audio_url: "https://cdn.sonauto.ai/generations2_altformats/audio_c5e63f7c-fc79-4322-808d-c09911af4713.wav",
    sections: [{
      end: 9.45,
      start: 0
    }]
  },
  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("sonauto/v2/inpaint", {
  input: {
    lyrics_prompt: "[Chorus]
  Pigs are soaring in the sky
  Wings of bacon flying by
  ",
    audio_url: "https://cdn.sonauto.ai/generations2_altformats/audio_c5e63f7c-fc79-4322-808d-c09911af4713.wav",
    sections: [{
      end: 9.45,
      start: 0
    }]
  },
  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("sonauto/v2/inpaint", {
  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("sonauto/v2/inpaint", {
  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#

tags list<string>

Tags/styles of the music to generate. You can view a list of all available tags at https://sonauto.ai/tag-explorer.

lyrics_prompt string* required

The lyrics sung in the generated song. An empty string will generate an instrumental track.

seed integer

The seed to use for generation. Will pick a random seed if not provided. Repeating a request with identical parameters (must use lyrics and tags, not prompt) and the same seed will generate the same song.

prompt_strength float

Controls how strongly your prompt influences the output. Greater values adhere more to the prompt but sound less natural. (This is CFG.) Default value: 2

balance_strength float

Greater means more natural vocals. Lower means sharper instrumentals. We recommend 0.7. Default value: 0.7

num_songs integer

Generating 2 songs costs 1.5x the price of generating 1 song. Also, note that using the same seed may not result in identical songs if the number of songs generated is changed. Default value: 1

output_format OutputFormatEnum

Default value: "wav"

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

output_bit_rate Enum

The bit rate to use for mp3 and m4a formats. Not available for other formats.

Possible enum values: 128, 192, 256, 320

audio_url string* required

The URL of the audio file to alter. Must be a valid publicly accessible URL.

sections list<InpaintSection>* required

List of sections to inpaint. Currently, only one section is supported so the list length must be 1.

selection_crop boolean

Crop to the selected region

{
  "tags": [
    "2020s",
    "dance pop",
    "pop rock",
    "indie pop",
    "bubblegum pop",
    "synthpop",
    "teen pop",
    "electropop"
  ],
  "lyrics_prompt": "[Chorus]\nPigs are soaring in the sky\nWings of bacon flying by\n",
  "prompt_strength": 2,
  "balance_strength": 0.7,
  "num_songs": 1,
  "output_format": "wav",
  "audio_url": "https://cdn.sonauto.ai/generations2_altformats/audio_c5e63f7c-fc79-4322-808d-c09911af4713.wav",
  "sections": [
    {
      "end": 9.45,
      "start": 0
    }
  ]
}

Output#

audio list<File>* required

The generated audio files.

seed integer* required

The seed used for generation. This can be used to generate an identical song by passing the same parameters with this seed in a future request.

{
  "audio": {
    "file_size": 16777294,
    "file_name": "sonauto.wav",
    "content_type": "audio/wav",
    "url": "https://cdn.sonauto.ai/generations2_altformats/audio_9a480c86-a3c0-46e5-bfb0-c0cd6e2fdbc6.wav"
  },
  "seed": 42
}

Other types#

InpaintSection#

start float* required

Start time in seconds of the section to inpaint.

end float* required

End time in seconds of the section to inpaint.

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