Spiral gives your agent every tool with one account. Browse the tools →

Hermes · Audio

How to Use ACE-Step Audio to Audio in Hermes

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 Hermes

Copy an example into Hermes, or ask in your own words.

Once a week, use ACE-Step Audio to Audio to remix my supplied instrumental theme recording in a different musical style. Alternate between jazz and acoustic folk, and label each take with its requested style.

ACE-Step Audio to AudioHermes
Try asking
  • Each month, use ACE-Step Audio to Audio to audition the next revised chorus from the lyric revisions I supplied against my original demo recording. Choose lyric editing and collect the result for review.

  • Every Monday at 9am: compose a 30-second upbeat lo-fi track with ACE-Step Audio to Audio for a product video.

  • 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 Hermes

Pick the way that suits you. Each takes about two minutes.

Use the Spiral skill

  1. Send Hermes this message

    Your agent reads Spiral's skill and sets itself up.

    set up https://spiral.ai/SKILL.md
  2. Sign in or paste a key

    Approve Spiral in the browser, or give the agent a key from the console.

Use Spiral's MCP server

  1. Add the server and sign in

    Hermes opens your browser: sign in to Spiral and click Authorize. No API key. When Hermes asks Enable all tools? \[Y/n/select], answer Y: n cancels without saving the server, and select hides the tools you leave out.

    hermes mcp add spiral \
      --url https://api.spiral.ai/mcp \
      --auth oauth \
      --connect-timeout 300
  2. Check it

    In a chat that was already open, run /reload-mcp.

    hermes mcp list
    hermes mcp test spiral

Use the Spiral CLI

  1. 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

  1. Create an API key

    In the console, under API keys.

  2. 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: Hermes 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.

falAudio
ACE Step · Audio to Audio
fal-ai/ace-step/audio-to-audio

Settings you can ask for

ACE-Step Audio to Audio works from your audio URL. Ask Hermes for any of these in your prompt.

SettingAllowed valuesDefaultDescription
Edit modelyrics or remixremix

Whether to edit the lyrics only or remix the audio.

Number of steps3 to 6027

Number of steps to generate the audio.

Seeda whole number

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

Schedulereuler or heuneuler

Scheduler to use for the generation process.

Guidance typecfg, apg, or cfg_starapg

Type of CFG to use for the generation process.

Granularity scale-100 to 10010

Granularity scale for the generation process. Higher values can reduce artifacts.

Guidance interval0 to 10.5

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 decay0 to 10

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 scale0 to 20015

Guidance scale for the generation.

Minimum guidance scale0 to 2003

Minimum guidance scale for the generation after the decay.

Tag guidance scale0 to 105

Tag guidance scale for the generation.

Lyric guidance scale0 to 101.5

Lyric guidance scale for the generation.

Original seeda 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 Hermes?

Build a recurring supply of music drafts for a series, game, or songwriting practice. Have the agent prepare ACE-Step takes on a schedule and collect them for listening and selection.

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.

Questions about ACE-Step Audio to Audio in Hermes

Can Hermes use ACE-Step Audio to Audio?

Yes. Add Spiral to Hermes as an MCP server, and Hermes can find and run ACE-Step Audio to Audio like any built-in tool.

How much does ACE-Step Audio to Audio cost in Hermes?

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 Hermes plan is separate.

Do I need a fal account to use ACE-Step Audio to Audio in Hermes?

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 Hermes?

About two minutes: add the server and sign in, then check it.

Does Hermes wait while ACE-Step Audio to Audio runs?

ACE-Step Audio to Audio runs in the background. Hermes 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.

Get started

Start using ACE-Step Audio to Audio in Hermes

One Spiral account for every tool your agent needs. No subscription; you pay per run.

Paste this into Hermes:

Set up Hermes

set up https://spiral.ai/SKILL.md
Are you an AI agent? See setup options