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

Muse Code · Audio

How to Use MiniMax Voice Design in Muse Code

MiniMax Voice Design creates a custom speaking voice from a written description, useful for auditioning narrators and characters. It returns a short preview and a voice ID for later speech generation.

Prompts to try with MiniMax Voice Design in Muse Code

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

Use MiniMax Voice Design to audition the shopkeeper in our dialogue files: an older man with a gravelly voice, dry humor, and measured delivery for an adult fantasy game. Choose one line under 500 characters and save the preview beside the character brief.

MiniMax Voice DesignMuse Code
Try asking
  • Read our onboarding copy and use MiniMax Voice Design to audition a woman in her thirties with a clear, warm voice and patient pacing for first-time users. Select a welcome message under 500 characters.

  • Use MiniMax Voice Design to create two auditions for the tutorial narrator described in our project notes. Keep the script under 500 characters and identical in both; change only the requested pacing.

  • From our story script, select a passage under 500 characters and use MiniMax Voice Design to audition an elderly storyteller with a soft, slightly raspy voice and gentle delivery for adult listeners.

  • Use MiniMax Voice Design to audition a calm adult male instructor for our help tutorial. Take a short explanation from the documentation, keep it under 500 characters, and save the voice description with the audio.

How to set up MiniMax Voice Design in Muse Code

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

Use Spiral's MCP server

  1. Install Muse Code
    curl -fsSL https://dev.meta.ai/install.sh | bash
  2. Ask Muse to add the server

    Start muse and ask:

    Add the Spiral MCP server at https://api.spiral.ai/mcp
  3. Sign in

    In your terminal, run:

    muse mcp login spiral

Use the Spiral skill

  1. Send Muse 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 MiniMax Voice Design

    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/minimax/voice-design",
        "input": {
          "prompt": "Bubbly and excitable female pop star interviewee, youthful, slightly breathless, and very enthusiastic",
          "preview_text": "Oh my gosh, hi. It'\''s like so amazing to be here. This new endpoint just dropped on fal and the results have been like totally incredible. Use it now, It'\''s gonna…"
        }
      }'

Then paste one of the prompts above: Muse Code finds MiniMax Voice Design on Spiral, shows the price and runs it.

MiniMax Voice Design providers and prices

Spiral runs MiniMax Voice Design through fal. Open a card for today's price, with every fee included.

falAudio
MiniMax Voice Design
fal-ai/minimax/voice-design

What can you do with MiniMax Voice Design in Muse Code?

Audition voices for game characters, onboarding, and spoken tutorials while working on the project. The agent can turn existing dialogue or interface copy into short tests and keep each description beside its preview.

Game character auditions

Try a gruff shopkeeper or a nervous apprentice on one short dialogue line before choosing the character's voice.

Audiobook narrator casting

Audition a narrator on a short passage containing description and dialogue before producing the book with text-to-speech.

Product assistant voice

Design a patient, conversational voice and test it on a welcome message and a correction.

Podcast host auditions

Compare host voice descriptions using the same opening sentence to judge warmth, pace, and vocal texture.

Training narrator selection

Audition a clear, measured instructor on a short explanation before recording a full course through text-to-speech.

Bedtime storyteller auditions

Test a gentle storyteller voice on a quiet scene, with the intended age of the audience included in the description.

Questions about MiniMax Voice Design in Muse Code

Can Muse Code use MiniMax Voice Design?

Yes. Add Spiral to Muse Code as an MCP server, and Muse Code can find and run MiniMax Voice Design like any built-in tool.

How much does MiniMax Voice Design cost in Muse Code?

Up to $3.9195 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 Muse Code plan is separate.

Do I need a fal account to use MiniMax Voice Design in Muse Code?

No. Spiral runs MiniMax Voice Design on its own fal account. You sign in to Spiral once and never paste a key.

How long does it take to set up MiniMax Voice Design in Muse Code?

About two minutes: install Muse Code, then ask Muse to add the server, then sign in.

Does Muse Code wait while MiniMax Voice Design runs?

MiniMax Voice Design runs in the background. Muse Code starts the run, checks on it and gives you the audio when it's ready.

What is MiniMax Voice Design useful for?

Use it to audition a custom narrator, fictional character, or product voice from a written brief. You get a short spoken sample before choosing a voice for further speech generation.

Does MiniMax Voice Design copy a recorded speaker?

MiniMax Voice Design creates a voice from a written description. MiniMax provides a separate voice cloning tool for working from recorded speech.

How long can the audition script be?

The script must contain 1 to 500 characters. Use a short excerpt to judge the voice; generate longer narration separately with text-to-speech.

What should I include in a voice description?

Specify age, gender, vocal texture, emotional tone, pacing, intended use, and audience. For example, describe an older storyteller with a soft, slightly raspy voice and unhurried delivery for adult listeners.

How should I compare voice auditions?

Keep the audition script the same and change one part of the description, such as pacing or vocal texture. Include a line your intended audience would actually hear.

Get started

Start using MiniMax Voice Design in Muse Code

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

Paste this into Muse Code:

Set up Muse Code

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