ACE Step · Audio to Audio
fal-ai/ace-step/audio-to-audioEdit and transform audio with ACE Step · Audio to Audio from fal through one Spiral API key. It runs in the background and returns audio. Pay as you go, with no subscription.
Pricing
$0.00026 per second.
Limits
- Runs
- In the background
- Returns
- audio
- Longest queue wait
- 1 hour
- Run deadline
- 30 minutes
- Longest run, end to end
- 255 minutes
- Largest inline input
- 1 MB
- Largest input file
- 2 GB
- Largest output
- 5 GB
Input
| Field | Kind | Default | Description |
|---|---|---|---|
audio_url required | URL or file | — | URL of the audio file to be outpainted. |
edit_mode | one of lyrics, remix | remix | Whether to edit the lyrics only or remix the audio. |
original_tags required | text | — | Original tags of the audio file. |
original_lyrics | text | Original lyrics of the audio file. | |
tags required | text | — | Comma-separated list of genre tags to control the style of the generated audio. Can also be supplied as |
lyrics | text | 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. | |
number_of_steps | number (whole) 3 to 60 | 27 | Number of steps to generate the audio. |
seed | number (whole) | — | Random seed for reproducibility. If not provided, a random seed will be used. |
scheduler | one of euler, heun | euler | Scheduler to use for the generation process. |
guidance_type | one of cfg, apg, cfg_star | apg | Type of CFG to use for the generation process. |
granularity_scale | number (whole) -100 to 100 | 10 | Granularity scale for the generation process. Higher values can reduce artifacts. |
guidance_interval | number 0 to 1 | 0.5 | Guidance interval for the generation. 0.5 means only apply guidance in the middle steps (0.25 * infer_steps to 0.75 * infer_steps) |
guidance_interval_decay | number 0 to 1 | 0 | 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 | number 0 to 200 | 15 | Guidance scale for the generation. |
minimum_guidance_scale | number 0 to 200 | 3 | Minimum guidance scale for the generation after the decay. |
tag_guidance_scale | number 0 to 10 | 5 | Tag guidance scale for the generation. |
lyric_guidance_scale | number 0 to 10 | 1.5 | Lyric guidance scale for the generation. |
original_seed | number (whole) | — | Original seed of the audio file. |
Same request in code
curl https://api.spiral.ai/v1/runs \
-H "Authorization: Bearer $SPIRAL_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{
"provider": "fal",
"model": "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"
}
}'Frequently asked questions
How much does ACE Step · Audio to Audio cost?
$0.00026 per second. You pay as you go from one Spiral balance, with no subscription, and a failed run is not charged.
How do I use ACE Step · Audio to Audio through an API?
Send `POST /v1/runs` with `"provider": "fal"`, `"model": "fal-ai/ace-step/audio-to-audio"` and the input fields on this page, using one Spiral API key. It runs in the background: poll the run, or name a webhook to be told when it finishes.
Do I need an account with fal to use ACE Step · Audio to Audio?
No. Spiral runs it on its own fal account and charges your Spiral balance.
Can my AI agent use ACE Step · Audio to Audio?
Yes. Agents find and run it through Spiral's MCP server, CLI or agent skill, with the same API key.