ACE-Step | Audio to Audio

fal-ai/ace-step/audio-inpaint

Modify a portion of provided audio with lyrics and/or style using ACE-Step

Inference

Commercial use

Schema

Playground API

About

Inpaint audio using the ACE-Step model.

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

Migrate to @fal-ai/client

The @fal-ai/serverless-client package has been deprecated in favor of @fal-ai/client. Please check the migration guide for more information.

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/ace-step/audio-inpaint", {
  input: {
    audio_url: "https://storage.googleapis.com/falserverless/example_inputs/ace-step-audio-to-audio.wav",
    tags: "lofi, hiphop, drum and bass, trap, chill"
  },
  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"
});

Protect your API 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.

3. Queue#

Long-running requests

For long-running requests, such as training jobs or models with slower inference times, it is recommended to check the Queue status and rely on Webhooks instead of blocking while waiting for the result.

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/ace-step/audio-inpaint", {
  input: {
    audio_url: "https://storage.googleapis.com/falserverless/example_inputs/ace-step-audio-to-audio.wav",
    tags: "lofi, hiphop, drum and bass, trap, chill"
  },
  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/ace-step/audio-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("fal-ai/ace-step/audio-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);

Auto uploads

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.

5. Schema#

Input#

audio_url string* required

URL of the audio file to be inpainted.

start_time_relative_to StartTimeRelativeToEnum

Whether the start time is relative to the start or end of the audio. Default value: "start"

Possible enum values: start, end

start_time float

start time in seconds for the inpainting process.

end_time_relative_to EndTimeRelativeToEnum

Whether the end time is relative to the start or end of the audio. Default value: "start"

Possible enum values: start, end

end_time float

end time in seconds for the inpainting process. Default value: 30

tags string* required

Comma-separated list of genre tags to control the style of the generated audio.

lyrics string

Lyrics to be sung in the audio. If not provided or if [inst] or [instrumental] is the content of this field, no lyrics will be sung. Use control structures like [verse], [chorus] and [bridge] to control the structure of the song. Default value: ""

variance float

Variance for the inpainting process. Higher values can lead to more diverse results. Default value: 0.5

number_of_steps integer

Number of steps to generate the audio. Default value: 27

seed integer

Random seed for reproducibility. If not provided, a random seed will be used.

scheduler SchedulerEnum

Scheduler to use for the generation process. Default value: "euler"

Possible enum values: euler, heun

guidance_type GuidanceTypeEnum

Type of CFG to use for the generation process. Default value: "apg"

Possible enum values: cfg, apg, cfg_star

granularity_scale integer

Granularity scale for the generation process. Higher values can reduce artifacts. Default value: 10

guidance_interval float

Guidance interval for the generation. 0.5 means only apply guidance in the middle steps (0.25 * infer_steps to 0.75 * infer_steps) Default value: 0.5

guidance_interval_decay float

Guidance interval decay for the generation. Guidance scale will decay from guidance_scale to min_guidance_scale in the interval. 0.0 means no decay.

guidance_scale float

Guidance scale for the generation. Default value: 15

minimum_guidance_scale float

Minimum guidance scale for the generation after the decay. Default value: 3

tag_guidance_scale float

Tag guidance scale for the generation. Default value: 5

lyric_guidance_scale float

Lyric guidance scale for the generation. Default value: 1.5

{
  "audio_url": "https://storage.googleapis.com/falserverless/example_inputs/ace-step-audio-to-audio.wav",
  "start_time_relative_to": "start",
  "start_time": 0,
  "end_time_relative_to": "start",
  "end_time": 30,
  "tags": "lofi, hiphop, drum and bass, trap, chill",
  "variance": 0.5,
  "number_of_steps": 27,
  "scheduler": "euler",
  "guidance_type": "apg",
  "granularity_scale": 10,
  "guidance_interval": 0.5,
  "guidance_interval_decay": 0,
  "guidance_scale": 15,
  "minimum_guidance_scale": 3,
  "tag_guidance_scale": 5,
  "lyric_guidance_scale": 1.5
}

Output#

audio File* required

The generated audio file.

seed integer* required

The random seed used for the generation process.

tags string* required

The genre tags used in the generation process.

lyrics string* required

The lyrics used in the generation process.

{
  "audio": {
    "url": "https://storage.googleapis.com/falserverless/example_outputs/ace-step-audio-inpaint.wav"
  },
  "seed": 42,
  "tags": "lofi, hiphop, drum and bass, trap, chill",
  "lyrics": "[inst]"
}

Other types#

ACEStepAudioToAudioResponse#

audio File* required

The generated audio file.

seed integer* required

The random seed used for the generation process.

tags string* required

The genre tags used in the generation process.

lyrics string* required

The lyrics used in the generation process.

ACEStepResponse#

audio File* required

The generated audio file.

seed integer* required

The random seed used for the generation process.

tags string* required

The genre tags used in the generation process.

lyrics string* required

The lyrics used in the generation process.

ACEStepTextToAudioRequest#

tags string* required

Comma-separated list of genre tags to control the style of the generated audio.

lyrics string

duration float

The duration of the generated audio in seconds. Default value: 60

number_of_steps integer

Number of steps to generate the audio. Default value: 27

seed integer

Random seed for reproducibility. If not provided, a random seed will be used.

scheduler SchedulerEnum

Scheduler to use for the generation process. Default value: "euler"

Possible enum values: euler, heun

guidance_type GuidanceTypeEnum

Type of CFG to use for the generation process. Default value: "apg"

Possible enum values: cfg, apg, cfg_star

granularity_scale integer

Granularity scale for the generation process. Higher values can reduce artifacts. Default value: 10

guidance_interval float

Guidance interval for the generation. 0.5 means only apply guidance in the middle steps (0.25 * infer_steps to 0.75 * infer_steps) Default value: 0.5

guidance_interval_decay float

Guidance interval decay for the generation. Guidance scale will decay from guidance_scale to min_guidance_scale in the interval. 0.0 means no decay.

guidance_scale float

Guidance scale for the generation. Default value: 15

minimum_guidance_scale float

Minimum guidance scale for the generation after the decay. Default value: 3

tag_guidance_scale float

Tag guidance scale for the generation. Default value: 5

lyric_guidance_scale float

Lyric guidance scale for the generation. Default value: 1.5

ACEStepAudioToAudioRequest#

audio_url string* required

URL of the audio file to be outpainted.

edit_mode EditModeEnum

Whether to edit the lyrics only or remix the audio. Default value: "remix"

Possible enum values: lyrics, remix

original_tags string* required

Original tags of the audio file.

original_lyrics string

Original lyrics of the audio file. Default value: ""

tags string* required

Comma-separated list of genre tags to control the style of the generated audio.

lyrics string

number_of_steps integer

Number of steps to generate the audio. Default value: 27

seed integer

Random seed for reproducibility. If not provided, a random seed will be used.

scheduler SchedulerEnum

Scheduler to use for the generation process. Default value: "euler"

Possible enum values: euler, heun

guidance_type GuidanceTypeEnum

Type of CFG to use for the generation process. Default value: "apg"

Possible enum values: cfg, apg, cfg_star

granularity_scale integer

Granularity scale for the generation process. Higher values can reduce artifacts. Default value: 10

guidance_interval float

Guidance interval for the generation. 0.5 means only apply guidance in the middle steps (0.25 * infer_steps to 0.75 * infer_steps) Default value: 0.5

guidance_interval_decay float

Guidance interval decay for the generation. Guidance scale will decay from guidance_scale to min_guidance_scale in the interval. 0.0 means no decay.

guidance_scale float

Guidance scale for the generation. Default value: 15

minimum_guidance_scale float

Minimum guidance scale for the generation after the decay. Default value: 3

tag_guidance_scale float

Tag guidance scale for the generation. Default value: 5

lyric_guidance_scale float

Lyric guidance scale for the generation. Default value: 1.5

original_seed integer

Original seed of the audio file.

ACEStepAudioOutpaintRequest#

audio_url string* required

URL of the audio file to be outpainted.

extend_before_duration float

Duration in seconds to extend the audio from the start.

extend_after_duration float

Duration in seconds to extend the audio from the end. Default value: 30

tags string* required

Comma-separated list of genre tags to control the style of the generated audio.

lyrics string

number_of_steps integer

Number of steps to generate the audio. Default value: 27

seed integer

Random seed for reproducibility. If not provided, a random seed will be used.

scheduler SchedulerEnum

Scheduler to use for the generation process. Default value: "euler"

Possible enum values: euler, heun

guidance_type GuidanceTypeEnum

Type of CFG to use for the generation process. Default value: "apg"

Possible enum values: cfg, apg, cfg_star

granularity_scale integer

Granularity scale for the generation process. Higher values can reduce artifacts. Default value: 10

guidance_interval float

Guidance interval for the generation. 0.5 means only apply guidance in the middle steps (0.25 * infer_steps to 0.75 * infer_steps) Default value: 0.5

guidance_interval_decay float

Guidance interval decay for the generation. Guidance scale will decay from guidance_scale to min_guidance_scale in the interval. 0.0 means no decay.

guidance_scale float

Guidance scale for the generation. Default value: 15

minimum_guidance_scale float

Minimum guidance scale for the generation after the decay. Default value: 3

tag_guidance_scale float

Tag guidance scale for the generation. Default value: 5

lyric_guidance_scale float

Lyric guidance scale for the generation. Default value: 1.5

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.

file_data string

File data

ACEStepPromptToAudioRequest#

prompt string* required

Prompt to control the style of the generated audio. This will be used to generate tags and lyrics.

instrumental boolean

Whether to generate an instrumental version of the audio.

duration float

The duration of the generated audio in seconds. Default value: 60

number_of_steps integer

Number of steps to generate the audio. Default value: 27

seed integer

Random seed for reproducibility. If not provided, a random seed will be used.

scheduler SchedulerEnum

Scheduler to use for the generation process. Default value: "euler"

Possible enum values: euler, heun

guidance_type GuidanceTypeEnum

Type of CFG to use for the generation process. Default value: "apg"

Possible enum values: cfg, apg, cfg_star

granularity_scale integer

Granularity scale for the generation process. Higher values can reduce artifacts. Default value: 10

guidance_interval float

Guidance interval for the generation. 0.5 means only apply guidance in the middle steps (0.25 * infer_steps to 0.75 * infer_steps) Default value: 0.5

guidance_interval_decay float

Guidance interval decay for the generation. Guidance scale will decay from guidance_scale to min_guidance_scale in the interval. 0.0 means no decay.

guidance_scale float

Guidance scale for the generation. Default value: 15

minimum_guidance_scale float

Minimum guidance scale for the generation after the decay. Default value: 3

tag_guidance_scale float

Tag guidance scale for the generation. Default value: 5

lyric_guidance_scale float

Lyric guidance scale for the generation. Default value: 1.5

Table of contents

1. Calling the API

2. Authentication

3. Queue

4. Files

5. Schema

About

1. Calling the API#

Install the client#

Migrate to @fal-ai/client

Setup your API Key#

Submit a request#

2. Authentication#

API Key#

Protect your API Key

3. Queue#

Long-running requests

Submit a request#

Fetch request status#

Get the result#

4. Files#

Data URI (base64)#

Hosted files (URL)#

Uploading files#

Auto uploads

5. Schema#

Input#

Output#

Other types#

ACEStepAudioToAudioResponse#

ACEStepResponse#

ACEStepTextToAudioRequest#

ACEStepAudioToAudioRequest#

ACEStepAudioOutpaintRequest#

File#

ACEStepPromptToAudioRequest#

Related Models

ACE-Step Audio to Audio

Table of contents

1. Calling the API

2. Authentication

3. Queue

4. Files

5. Schema

About

1. Calling the API#

Install the client#

Migrate to @fal-ai/client

Setup your API Key#

Submit a request#

2. Authentication#

API Key#

Protect your API Key

3. Queue#

Long-running requests

Submit a request#

Fetch request status#

Get the result#

4. Files#

Data URI (base64)#

Hosted files (URL)#

Uploading files#

Auto uploads

5. Schema#

Input#

Output#

Other types#

ACEStepAudioToAudioResponse#

ACEStepResponse#

ACEStepTextToAudioRequest#

ACEStepAudioToAudioRequest#

ACEStepAudioOutpaintRequest#

File#

ACEStepPromptToAudioRequest#

Related Models