Ace Step Audio To Audio
Playground
Try it on WavespeedAI!ACE-Step Audio-to-Audio model generates music variations from existing audio files. It can remix existing tracks or edit lyrics while preserving the original audio’s characteristics. Choose between ‘remix’ mode to transform the style while keeping structure, or ‘lyrics’ mode to modify the vocal content.
Features
ACE-Step: Audio to Audio
ACE-Step Audio-to-Audio model generates music variations from existing audio files.
Key Features
- Remix Mode: Transform the musical style while preserving structural elements.
- Lyrics Mode: Edit and modify vocal content while keeping the music intact.
- Style Control: Use genre tags to guide the output style.
- High Quality: Maintains fine-grained acoustic details from the original.
Use Cases
- Remix existing tracks with different genres
- Edit lyrics while keeping the instrumental backing
- Create variations of a song for A/B testing
- Adapt music for different contexts
Pricing
$0.0002 per second of generated audio.
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/ace-step/audio-to-audio" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
"edit_mode": "remix",
"original_lyrics": "",
"lyrics": "",
"seed": -1
}'
# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"
Parameters
Task Submission Parameters
Request Parameters
Parameter | Type | Required | Default | Range | Description |
---|---|---|---|---|---|
audio | string | Yes | - | - | Audio file to transcribe. Provide an HTTPS URL or upload a file (MP3, WAV, FLAC up to 60 minutes). |
original_tags | string | Yes | - | - | Original genre tags of the audio file. |
tags | string | Yes | - | - | Comma-separated list of genre tags to control the style. |
edit_mode | string | No | remix | lyrics, remix | Edit mode: lyrics or remix. |
original_lyrics | string | No | - | - | Original lyrics of the audio. |
lyrics | string | No | - | - | New lyrics for generation. |
seed | integer | No | -1 | -1 ~ 2147483647 | The random seed for reproducibility. |
Response Parameters
Parameter | Type | Description |
---|---|---|
code | integer | HTTP status code (e.g., 200 for success) |
message | string | Status message (e.g., “success”) |
data.id | string | Unique identifier for the prediction, Task Id |
data.model | string | Model ID used for the prediction |
data.outputs | array | Array of URLs to the generated content (empty when status is not completed ) |
data.urls | object | Object containing related API endpoints |
data.urls.get | string | URL to retrieve the prediction result |
data.has_nsfw_contents | array | Array of boolean values indicating NSFW detection for each output |
data.status | string | Status of the task: created , processing , completed , or failed |
data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
data.error | string | Error message (empty if no error occurred) |
data.timings | object | Object containing timing details |
data.timings.inference | integer | Inference time in milliseconds |