# ACE-Step > Generate music from a lyrics and example audio using ACE-Step ## Overview - **Endpoint**: `https://fal.run/fal-ai/ace-step/audio-to-audio` - **Model ID**: `fal-ai/ace-step/audio-to-audio` - **Category**: audio-to-audio - **Kind**: inference **Tags**: audio-to-audio, audio-edit ## Pricing Your request will cost $0.0002 per second of generated audio. For $1 you can run generate 5000 seconds (83 minutes) of music from lyrics. For more details, see [fal.ai pricing](https://fal.ai/pricing). ## API Information This model can be used via our HTTP API or more conveniently via our client libraries. See the input and output schema below, as well as the usage examples. ### Input Schema The API accepts the following input parameters: - **`audio_url`** (`string`, _required_): URL of the audio file to be outpainted. - Examples: "https://storage.googleapis.com/falserverless/example_inputs/ace-step-audio-to-audio.wav" - **`edit_mode`** (`EditModeEnum`, _optional_): Whether to edit the lyrics only or remix the audio. Default value: `"remix"` - Default: `"remix"` - Options: `"lyrics"`, `"remix"` - Examples: "remix" - **`original_tags`** (`string`, _required_): Original tags of the audio file. - Examples: "lofi, hiphop, drum and bass, trap, chill" - **`original_lyrics`** (`string`, _optional_): Original lyrics of the audio file. Default value: `""` - Default: `""` - Examples: "" - **`tags`** (`string`, _required_): Comma-separated list of genre tags to control the style of the generated audio. - Examples: "lofi, hiphop, drum and bass, trap, chill" - **`lyrics`** (`string`, _optional_): 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: `""` - Default: `""` - **`number_of_steps`** (`integer`, _optional_): Number of steps to generate the audio. Default value: `27` - Default: `27` - Range: `3` to `60` - Examples: 27 - **`seed`** (`integer`, _optional_): Random seed for reproducibility. If not provided, a random seed will be used. - **`scheduler`** (`SchedulerEnum`, _optional_): Scheduler to use for the generation process. Default value: `"euler"` - Default: `"euler"` - Options: `"euler"`, `"heun"` - Examples: "euler" - **`guidance_type`** (`GuidanceTypeEnum`, _optional_): Type of CFG to use for the generation process. Default value: `"apg"` - Default: `"apg"` - Options: `"cfg"`, `"apg"`, `"cfg_star"` - Examples: "apg" - **`granularity_scale`** (`integer`, _optional_): Granularity scale for the generation process. Higher values can reduce artifacts. Default value: `10` - Default: `10` - Range: `-100` to `100` - Examples: 10 - **`guidance_interval`** (`float`, _optional_): 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` - Default: `0.5` - Range: `0` to `1` - Examples: 0.5 - **`guidance_interval_decay`** (`float`, _optional_): 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. - Default: `0` - Range: `0` to `1` - Examples: 0 - **`guidance_scale`** (`float`, _optional_): Guidance scale for the generation. Default value: `15` - Default: `15` - Range: `0` to `200` - Examples: 15 - **`minimum_guidance_scale`** (`float`, _optional_): Minimum guidance scale for the generation after the decay. Default value: `3` - Default: `3` - Range: `0` to `200` - Examples: 3 - **`tag_guidance_scale`** (`float`, _optional_): Tag guidance scale for the generation. Default value: `5` - Default: `5` - Range: `0` to `10` - Examples: 5 - **`lyric_guidance_scale`** (`float`, _optional_): Lyric guidance scale for the generation. Default value: `1.5` - Default: `1.5` - Range: `0` to `10` - Examples: 1.5 - **`original_seed`** (`integer`, _optional_): Original seed of the audio file. **Required Parameters Example**: ```json { "audio_url": "https://storage.googleapis.com/falserverless/example_inputs/ace-step-audio-to-audio.wav", "original_tags": "lofi, hiphop, drum and bass, trap, chill", "tags": "lofi, hiphop, drum and bass, trap, chill" } ``` **Full Example**: ```json { "audio_url": "https://storage.googleapis.com/falserverless/example_inputs/ace-step-audio-to-audio.wav", "edit_mode": "remix", "original_tags": "lofi, hiphop, drum and bass, trap, chill", "original_lyrics": "", "tags": "lofi, hiphop, drum and bass, trap, chill", "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 Schema The API returns the following output format: - **`audio`** (`File`, _required_): The generated audio file. - Examples: {"url":"https://storage.googleapis.com/falserverless/example_outputs/ace-step-audio-to-audio.wav"} - **`seed`** (`integer`, _required_): The random seed used for the generation process. - Examples: 42 - **`tags`** (`string`, _required_): The genre tags used in the generation process. - Examples: "lofi, hiphop, drum and bass, trap, chill" - **`lyrics`** (`string`, _required_): The lyrics used in the generation process. - Examples: "[inst]" **Example Response**: ```json { "audio": { "url": "https://storage.googleapis.com/falserverless/example_outputs/ace-step-audio-to-audio.wav" }, "seed": 42, "tags": "lofi, hiphop, drum and bass, trap, chill", "lyrics": "[inst]" } ``` ## Usage Examples ### cURL ```bash curl --request POST \ --url https://fal.run/fal-ai/ace-step/audio-to-audio \ --header "Authorization: Key $FAL_KEY" \ --header "Content-Type: application/json" \ --data '{ "audio_url": "https://storage.googleapis.com/falserverless/example_inputs/ace-step-audio-to-audio.wav", "original_tags": "lofi, hiphop, drum and bass, trap, chill", "tags": "lofi, hiphop, drum and bass, trap, chill" }' ``` ### Python Ensure you have the Python client installed: ```bash pip install fal-client ``` Then use the API client to make requests: ```python import fal_client def on_queue_update(update): if isinstance(update, fal_client.InProgress): for log in update.logs: print(log["message"]) result = fal_client.subscribe( "fal-ai/ace-step/audio-to-audio", arguments={ "audio_url": "https://storage.googleapis.com/falserverless/example_inputs/ace-step-audio-to-audio.wav", "original_tags": "lofi, hiphop, drum and bass, trap, chill", "tags": "lofi, hiphop, drum and bass, trap, chill" }, with_logs=True, on_queue_update=on_queue_update, ) print(result) ``` ### JavaScript Ensure you have the JavaScript client installed: ```bash npm install --save @fal-ai/client ``` Then use the API client to make requests: ```javascript import { fal } from "@fal-ai/client"; const result = await fal.subscribe("fal-ai/ace-step/audio-to-audio", { input: { audio_url: "https://storage.googleapis.com/falserverless/example_inputs/ace-step-audio-to-audio.wav", original_tags: "lofi, hiphop, drum and bass, trap, chill", 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); ``` ## Additional Resources ### Documentation - [Model Playground](https://fal.ai/models/fal-ai/ace-step/audio-to-audio) - [API Documentation](https://fal.ai/models/fal-ai/ace-step/audio-to-audio/api) - [OpenAPI Schema](https://fal.ai/api/openapi/queue/openapi.json?endpoint_id=fal-ai/ace-step/audio-to-audio) ### fal.ai Platform - [Platform Documentation](https://docs.fal.ai) - [Python Client](https://docs.fal.ai/clients/python) - [JavaScript Client](https://docs.fal.ai/clients/javascript)