How to Use ACE-Step Audio to Audio in Cursor
ACE-Step Audio to Audio works from an existing recording for lyric edits and remixes. Unlike ACE-Step Lyrics to Audio, it gives you a way to revise recorded music instead of starting from text alone.
Prompts to try with ACE-Step Audio to Audio in Cursor
Copy an example into Cursor, or ask in your own words.
Use ACE-Step Audio to Audio to remix the project's existing exploration cue with a quieter musical treatment. Keep it instrumental and save the result beside the original for comparison.
Use ACE-Step Audio to Audio to audition the revised chorus lyrics in the project's existing song demo. Read the original and revised lyric documents, choose lyric editing, and save a separate take for review.
Compose a 30-second upbeat lo-fi track with ACE-Step Audio to Audio for a product video. Save the result in ./assets.
Make a calm piano loop with ACE-Step Audio to Audio for a meditation app.
Create a cinematic 20-second intro sting with ACE-Step Audio to Audio.
How to set up ACE-Step Audio to Audio in Cursor
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the hosted server
Use Add to Cursor on the console's Agents & MCP page, or add this to .cursor/mcp.json (one project) or ~/.cursor/mcp.json (every project):
{ "mcpServers": { "spiral": { "url": "https://api.spiral.ai/mcp" } } } - Sign in
Open Cursor Settings › MCP, click Connect next to spiral, sign in to Spiral and click Authorize. No API key. Spiral then shows as connected, with its tools listed.
Use the Spiral skill
- Send Cursor this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run ACE-Step Audio to Audio
One request; the result comes back by polling or a webhook.
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" } }'
Then paste one of the prompts above: Cursor finds ACE-Step Audio to Audio on Spiral, shows the price and runs it.
ACE-Step Audio to Audio providers and prices
Spiral runs ACE-Step Audio to Audio through fal. Open a card for today's price, with every fee included.
Settings you can ask for
ACE-Step Audio to Audio works from your audio URL. Ask Cursor for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Edit mode | lyrics or remix | remix | Whether to edit the lyrics only or remix the audio. |
| Number of steps | 3 to 60 | 27 | Number of steps to generate the audio. |
| Seed | a whole number | Random seed for reproducibility. If not provided, a random seed will be used. | |
| Scheduler | euler or heun | euler | Scheduler to use for the generation process. |
| Guidance type | cfg, apg, or cfg_star | apg | Type of CFG to use for the generation process. |
| Granularity scale | -100 to 100 | 10 | Granularity scale for the generation process. Higher values can reduce artifacts. |
| Guidance interval | 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 | 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 | 0 to 200 | 15 | Guidance scale for the generation. |
| Minimum guidance scale | 0 to 200 | 3 | Minimum guidance scale for the generation after the decay. |
| Tag guidance scale | 0 to 10 | 5 | Tag guidance scale for the generation. |
| Lyric guidance scale | 0 to 10 | 1.5 | Lyric guidance scale for the generation. |
| Original seed | a whole number | Original seed of the audio file. |
Every API field of ACE Step · Audio to Audio is on its tool page: open its card above.
What can you do with ACE-Step Audio to Audio in Cursor?
Turn a project's music briefs into playable drafts for games, demos, and other prototypes. Use ACE-Step takes to compare musical directions alongside the scenes or features they accompany.
Songwriting demos
Audition a verse and chorus as a new song, or revise an existing demo to compare another lyrical or musical direction.
Podcast theme drafts
Create an instrumental theme from a brief, or remix an existing theme recording to explore a different treatment.
Game soundtrack sketches
Explore music for a menu, quiet exploration scene, or tense encounter. Start with a written brief or an existing music sketch, then audition the result against the scene.
Short video backing
Draft instrumental backing for a product demonstration or travel edit, either from a musical description or by remixing an existing cue.
Lyric delivery experiments
Hear how written lines sound in a new song or an edited recording. Compare phrasing and pronunciation before choosing a take.
Recorded lyric revisions
Use an existing song recording and revised lyrics to audition a change to the words.
Remix exploration
Use a recorded song as the starting point for a different musical treatment, then compare the result with the original.
More on ACE-Step Audio to Audio and Cursor
Overview
ACE-Step Audio to Audio in other agents
Questions about ACE-Step Audio to Audio in Cursor
Can Cursor use ACE-Step Audio to Audio?
Yes. Add Spiral to Cursor as an MCP server, and Cursor can find and run ACE-Step Audio to Audio like any built-in tool.
How much does ACE-Step Audio to Audio cost in Cursor?
Up to $0.0156 per run at the default inputs for 60 seconds of input. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Cursor plan is separate.
Do I need a fal account to use ACE-Step Audio to Audio in Cursor?
No. Spiral runs ACE-Step Audio to Audio on its own fal account. You sign in to Spiral once and never paste a key.
How long does it take to set up ACE-Step Audio to Audio in Cursor?
About two minutes: add the hosted server, then sign in.
Does Cursor wait while ACE-Step Audio to Audio runs?
ACE-Step Audio to Audio runs in the background. Cursor starts the run, checks on it and gives you the audio when it's ready.
What is ACE-Step useful for?
Use ACE-Step to audition song ideas, instrumental backing, and alternate musical treatments. It is a practical choice for drafts you can listen to and revise before committing to a production.
How should I write an ACE-Step music brief?
Keep the musical description separate from the words to be sung. Start with a focused brief such as acoustic folk, guitar, gentle percussion, and a restrained vocal, then place the lyrics in their own section.
Can ACE-Step make instrumentals?
Yes. Use [instrumental] or [inst] in place of sung lyrics, and describe the instrumentation and mood in the musical brief.
How do I indicate song sections?
Place [verse], [chorus], and [bridge] before the corresponding lyrics. Treat these as structural guidance and listen to the result before assuming the arrangement follows every instruction.
Does ACE-Step perform equally well in every language?
No. The model card says performance varies by language and is strongest in its top ten languages, so audition pronunciation before using a take.
Start using ACE-Step Audio to Audio in Cursor
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Cursor:
set up https://spiral.ai/SKILL.md


