[Integrations](https://spiral.ai/integrations) › [Muse Code](https://spiral.ai/integrations/muse-code) › [GPT-4o mini TTS](https://spiral.ai/integrations/muse-code/gpt-4o-mini-tts)

# How to Use GPT-4o mini TTS in Muse Code

GPT-4o mini TTS turns scripts into narration for demos, readouts, and support messages. Written delivery directions let you shape its tone, pacing, and emphasis.

|  |  |
| --- | --- |
| Model | GPT-4o mini TTS |
| Available through | OpenAI |
| Category | Audio |
| Price | Input text: $0.78 per 1M tokens. Output speech: $15.60 per 1M audio tokens. |
| Returns | audio |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with GPT-4o mini TTS in Muse Code

- Read the README and draft a 100-word introduction to this project using only documented behavior. Use GPT-4o mini TTS to narrate it with a clear, measured delivery, and save the script beside the audio.
- Find the main user tutorial and turn its first task into a short voiceover. Use GPT-4o mini TTS with a patient tone and pauses between actions; keep the script under 1,000 characters.
- Summarize the latest changelog entry in 80 words, then narrate it with GPT-4o mini TTS. Use a matter-of-fact tone and emphasize the changes users will notice.
- Find the project's telephone menu text and generate each menu option separately with GPT-4o mini TTS. Keep the delivery slow and even, and emphasize the option numbers.
- Take the shortest product demo script in this project and make two readings with GPT-4o mini TTS: one calm and measured, one upbeat and brisk. Keep the spoken words identical for comparison.

## How to set up GPT-4o mini TTS in Muse Code

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

### Use Spiral's MCP server

1. **Install Muse Code**

```bash
curl -fsSL https://dev.meta.ai/install.sh | bash
```

2. **Ask Muse to add the server**: Start `muse` and ask:

```text
Add the Spiral MCP server at https://api.spiral.ai/mcp
```

3. **Sign in**: In your terminal, run:

```bash
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.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run GPT-4o mini TTS**: One request; the result comes back by polling or a webhook.

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "openai",
    "model": "gpt-4o-mini-tts",
    "input": {
      "input": "<input>",
      "voice": "ash"
    }
  }'
```

Then paste one of the prompts above: Muse Code finds GPT-4o mini TTS on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/muse-code

## GPT-4o mini TTS tools and prices

- [GPT-4o mini TTS](https://spiral.ai/tools/openai/gpt-4o-mini-tts) (OpenAI): Input text: $0.78 per 1M tokens. Output speech: $15.60 per 1M audio tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| speed | 0.25 to 4 | 1 | The speed of the generated audio. Select a value from `0.25` to `4.0`. `1.0` is the default. |
| instructions |  | — | Control the voice of your generated audio with additional instructions. Does not work with `tts-1` or `tts-1-hd`. |
| response_format | mp3, opus, aac, flac, wav, pcm | mp3 | The format to audio in. Supported formats are `mp3`, `opus`, `aac`, `flac`, `wav`, and `pcm`. |

## What can you do with GPT-4o mini TTS in Muse Code?

Add spoken walkthroughs, help readouts, and release summaries to your project with GPT-4o mini TTS. Have the coding agent prepare short scripts from project files and keep delivery directions separate.

### Product walkthrough narration

Turn a short walkthrough script into speech. Ask for measured pacing and emphasis on the action viewers should take next.

### Spoken information readouts

Read help text, instructions, or short articles aloud with clear pronunciation and pauses between sections.

### Customer support messages

Voice approved support responses with a calm, reassuring delivery. Keep the explanation and next action easy to hear.

### Telephone menu recordings

Generate separate spoken menu options. Use an even pace and emphasize each option number.

### Localized narration

Generate speech from translated scripts in supported languages. Check pronunciation before using the recordings.

### Short story narration

Give a finished story a spoken delivery with directions for mood, pace, and emphasis. Divide longer stories into short passages.

### Recurring spoken briefings

Have an agent prepare a concise daily update, then narrate that script with a consistent delivery brief.

## Overview

- [OpenAI](https://spiral.ai/providers/openai)
- [All Muse Code guides](https://spiral.ai/integrations/muse-code)

## GPT-4o mini TTS in other agents

- [Amp](https://spiral.ai/integrations/amp/gpt-4o-mini-tts)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/gpt-4o-mini-tts)
- [Claude](https://spiral.ai/integrations/claude-desktop/gpt-4o-mini-tts)
- [Claude Code](https://spiral.ai/integrations/claude-code/gpt-4o-mini-tts)
- [Cline](https://spiral.ai/integrations/cline/gpt-4o-mini-tts)
- [Codex](https://spiral.ai/integrations/codex/gpt-4o-mini-tts)
- [Cursor](https://spiral.ai/integrations/cursor/gpt-4o-mini-tts)
- [Devin](https://spiral.ai/integrations/devin/gpt-4o-mini-tts)
- [dots](https://spiral.ai/integrations/dots/gpt-4o-mini-tts)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/gpt-4o-mini-tts)
- [Gemini](https://spiral.ai/integrations/gemini/gpt-4o-mini-tts)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/gpt-4o-mini-tts)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/gpt-4o-mini-tts)
- [goose](https://spiral.ai/integrations/goose/gpt-4o-mini-tts)
- [Grok](https://spiral.ai/integrations/grok/gpt-4o-mini-tts)
- [Grok Build](https://spiral.ai/integrations/grok-build/gpt-4o-mini-tts)
- [Hermes](https://spiral.ai/integrations/hermes/gpt-4o-mini-tts)
- [Instinct](https://spiral.ai/integrations/instinct/gpt-4o-mini-tts)
- [Manus](https://spiral.ai/integrations/manus/gpt-4o-mini-tts)
- [Muse](https://spiral.ai/integrations/muse/gpt-4o-mini-tts)
- [n8n](https://spiral.ai/integrations/n8n/gpt-4o-mini-tts)
- [Notion](https://spiral.ai/integrations/notion/gpt-4o-mini-tts)
- [OpenClaw](https://spiral.ai/integrations/openclaw/gpt-4o-mini-tts)
- [opencode](https://spiral.ai/integrations/opencode/gpt-4o-mini-tts)
- [Perplexity](https://spiral.ai/integrations/perplexity/gpt-4o-mini-tts)
- [Raycast](https://spiral.ai/integrations/raycast/gpt-4o-mini-tts)
- [VS Code](https://spiral.ai/integrations/vscode/gpt-4o-mini-tts)
- [Windsurf](https://spiral.ai/integrations/windsurf/gpt-4o-mini-tts)
- [Zapier](https://spiral.ai/integrations/zapier/gpt-4o-mini-tts)

## More Muse Code guides

- [F5-TTS](https://spiral.ai/integrations/muse-code/f5-tts)
- [GPT-4o mini Transcribe](https://spiral.ai/integrations/muse-code/gpt-4o-mini-transcribe)
- [Elevenlabs Tts Eleven V3](https://spiral.ai/integrations/muse-code/elevenlabs-tts-eleven-v3)
- [Gemini 2.5 Flash TTS](https://spiral.ai/integrations/muse-code/gemini-2-5-flash-tts)
- [Elevenlabs Music v2.5](https://spiral.ai/integrations/muse-code/elevenlabs-music-v2-5)
- [Gemini 2.5 Pro Preview TTS](https://spiral.ai/integrations/muse-code/gemini-2-5-pro-preview-tts)

## Questions about GPT-4o mini TTS in Muse Code

**Can Muse Code use GPT-4o mini TTS?**

Yes. Add Spiral to Muse Code as an MCP server, and Muse Code can find and run GPT-4o mini TTS like any built-in tool.

**How much does GPT-4o mini TTS cost in Muse Code?**

Input text: $0.78 per 1M tokens. Output speech: $15.60 per 1M audio tokens. 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 an OpenAI account to use GPT-4o mini TTS in Muse Code?**

No. Spiral runs GPT-4o mini TTS on its own OpenAI account. You sign in to Spiral once and never paste a key.

**How long does it take to set up GPT-4o mini TTS in Muse Code?**

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

**Does Muse Code wait while GPT-4o mini TTS runs?**

GPT-4o mini TTS runs in the background. Muse Code starts the run, checks on it and gives you the audio when it's ready.

**What is GPT-4o mini TTS useful for?**

Use it to narrate product demos, read written information aloud, voice support messages, or tell short stories. It is especially useful when you need to give the narrator specific delivery directions.

**How do I control the delivery?**

Describe the tone, pace, and emphasis separately from the words to be spoken. For example: use a calm tone, keep a measured pace, and stress the next action.

**How much text can GPT-4o mini TTS read at once?**

Keep each passage within both limits: 4,096 characters and 2,000 input tokens. Split longer scripts into short sections before generating narration.

**Can GPT-4o mini TTS speak languages other than English?**

Yes, including Spanish, French, German, and Japanese. Supply text in the language you want spoken; the voices are optimized for English, so check pronunciation when preparing other languages.

**How can I improve acronyms and pauses?**

Write an acronym as spoken letters when needed, such as A-I. Use punctuation and short line breaks to guide pauses, then check the resulting narration.

