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

Claude Code · Audio

How to Use Stable Audio 3 Medium Audio to Audio in Claude Code

Stable Audio 3 Medium Audio to Audio reshapes recordings into new musical styles, moods, and textures. Unlike Stable Audio 3 Medium Text to Audio, it starts with audio, with noise level controlling how much of the original survives.

Prompts to try with Stable Audio 3 Medium Audio to Audio in Claude Code

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

Use Stable Audio 3 Medium Audio to Audio on the project's menu music recording to explore a warmer acoustic direction with nylon guitar, brushed percussion, and a relaxed mood. Keep the result 45 seconds.

Stable Audio 3 Medium Audio to AudioClaude Code
Try asking
  • Compose a 30-second upbeat lo-fi track with Stable Audio 3 Medium Audio to Audio for a product video. Save the result in ./assets.

  • Make a calm piano loop with Stable Audio 3 Medium Audio to Audio for a meditation app.

  • Create a cinematic 20-second intro sting with Stable Audio 3 Medium Audio to Audio.

  • Make three 15-second jingle options with Stable Audio 3 Medium Audio to Audio for a podcast ad break.

How to set up Stable Audio 3 Medium Audio to Audio in Claude Code

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

Use Spiral's MCP server

  1. Add the hosted server

    This adds Spiral to the current project. Add --scope user to use it in every project.

    claude mcp add --transport http spiral https://api.spiral.ai/mcp
  2. Sign in

    Start claude, type /mcp, choose spiral and Authenticate. Sign in to Spiral in the browser and click Authorize. No API key.

Use the Spiral skill

  1. Send Claude Code 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 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 Stable Audio 3 Medium 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/stable-audio-3/medium/audio-to-audio",
        "input": {
          "prompt": "bossa nova bassline",
          "audio_url": "https://storage.googleapis.com/falserverless/model_tests/diffrythm/rock_en.wav"
        }
      }'

Then paste one of the prompts above: Claude Code finds Stable Audio 3 Medium Audio to Audio on Spiral, shows the price and runs it.

Stable Audio 3 Medium Audio to Audio providers and prices

Spiral runs Stable Audio 3 Medium Audio to Audio through fal. Open a card for today's price, with every fee included.

falAudio
Stable Audio 3 Medium · Audio to Audio
fal-ai/stable-audio-3/medium/audio-to-audio

Settings you can ask for

Stable Audio 3 Medium Audio to Audio works from your prompt and audio URL. Ask Claude Code for any of these in your prompt.

SettingAllowed valuesDefaultDescription
Negative promptwhat to leave out, in words

Text description of qualities to avoid in the output.

Duration1 to 38030

Duration of the generated audio in seconds. The medium model supports up to 380 seconds (~6m20s).

Number of inference steps1 to 1008

Number of sampling steps. Post-trained (distilled) checkpoints look good with the default 8 and gain little from going higher.

Guidance scale0 to 251

Classifier-free guidance scale. Higher values follow the prompt more strictly. Only effective on base (non-distilled) checkpoints.

Seeda whole number

Random seed for reproducible outputs. Omit for a random seed.

Enable prompt expansionon or offoff

If True, the prompt will be expanded using an LLM for more detailed and higher quality results.

Output formatmp3, wav, flac, ogg, opus, m4a, or aacmp3

Container format for the generated audio output.

Init noise level0 to 10.9

How much noise to add to the source audio. 1.0 fully replaces the audio with noise (pure generation); 0.1 keeps the source close to the input. 0.5 sits halfway between.

Every API field of Stable Audio 3 Medium · Audio to Audio is on its tool page: open its card above.

What can you do with Stable Audio 3 Medium Audio to Audio in Claude Code?

Create music cues and sound effects for games, apps, and interactive projects while working on their code. Turn scene descriptions and audio briefs into focused requests with appropriate durations.

Podcast background music

Create a restrained instrumental bed with sparse percussion and a clear mood, then audition it beneath narration.

Game scene music

Draft ambient exploration cues, tense encounter music, or quiet menu tracks with a defined instrument palette.

Video music sketches

Explore instrumental directions for a rough cut by specifying mood, tempo, instrumentation, and the required cue length.

Solo instrument ideas

Request a bass phrase, guitar texture, or percussion part as material to audition and edit in a composition.

Short sound effects

Create impacts, mechanical sounds, and transition effects with specific sources, actions, and decay characteristics.

Ambient sound design

Develop sustained drones and atmospheric textures for film scenes, installations, or game environments.

Recording restyles

Use an existing instrumental recording as the starting point for a different mood, genre, or instrument treatment.

Questions about Stable Audio 3 Medium Audio to Audio in Claude Code

Can Claude Code use Stable Audio 3 Medium Audio to Audio?

Yes. Add Spiral to Claude Code as an MCP server, and Claude Code can find and run Stable Audio 3 Medium Audio to Audio like any built-in tool.

How much does Stable Audio 3 Medium Audio to Audio cost in Claude Code?

$0.05421 per run at the default inputs. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Claude Code plan is separate.

Do I need a fal account to use Stable Audio 3 Medium Audio to Audio in Claude Code?

No. Spiral runs Stable Audio 3 Medium 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 Stable Audio 3 Medium Audio to Audio in Claude Code?

About two minutes: add the hosted server, then sign in.

Does Claude Code wait while Stable Audio 3 Medium Audio to Audio runs?

Stable Audio 3 Medium Audio to Audio runs in the background. Claude Code starts the run, checks on it and gives you the audio when it's ready.

What is Stable Audio 3 Medium good at?

Instrumental music, ambient backgrounds, individual instrument parts, and sound effects. Useful briefs include a restrained podcast bed, a solo guitar phrase, or a short impact sound.

How long can Stable Audio 3 Medium audio be?

Up to 380 seconds, or 6 minutes and 20 seconds. Match the duration to the material: a brief sound effect usually needs much less time than an instrumental track.

Can Stable Audio 3 Medium sing lyrics or create a voice-over?

It is intended for instrumental music and sound effects, not intelligible singing or speech. You may still hear wordless vocal-like textures.

What should I put in a Stable Audio 3 Medium prompt?

Describe the genre, main instruments, mood, tempo, and recording character. For sound effects, describe the sound source, action, decay, and acoustic space.

Which prompt language works best?

Use English. The model was trained on English descriptions, and the maker warns that other languages underperform.

Get started

Start using Stable Audio 3 Medium Audio to Audio in Claude Code

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

Paste this into Claude Code:

Set up Claude Code

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