How to Use Chatterbox TTS in Muse Code
Chatterbox TTS turns English scripts into speech with voice cloning and adjustable emotional intensity. Unlike Chatterbox Multilingual, it focuses on English, making it useful for narration, character lines, and spoken replies.
Prompts to try with Chatterbox TTS in Muse Code
Copy an example into Muse Code, or ask in your own words.
Read the onboarding copy in this project and write a three-sentence English walkthrough. Generate each sentence separately with Chatterbox TTS, using emotional exaggeration of 0.5.
Find the game's opening dialogue in this project. Use Chatterbox TTS to audition its first line with exaggeration of 0.7 and guidance of 0.3; keep character names outside the spoken text.
Turn the latest release notes in this repository into a two-sentence English audio introduction with Chatterbox TTS. Read only the introduction, excluding Markdown headings and links.
Use Chatterbox TTS and my supplied voice recording to narrate the first paragraph of this project's tutorial. Generate two readings with the same script, changing only emotional exaggeration from 0.5 to 0.7.
Create an English spoken confirmation for this app's successful export action: 'Your export is ready. You can download it now.' Use Chatterbox TTS with exaggeration of 0.5 and guidance of 0.3, then add the audio to the project's assets.
How to set up Chatterbox TTS in Muse Code
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Install Muse Code
curl -fsSL https://dev.meta.ai/install.sh | bash
- Ask Muse to add the server
Start muse and ask:
Add the Spiral MCP server at https://api.spiral.ai/mcp
- Sign in
In your terminal, run:
muse mcp login spiral
Use the Spiral skill
- Send Muse Code 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 Chatterbox TTS
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/chatterbox/text-to-speech", "input": { "text": "I just found a hidden treasure in the backyard! Check it out!" } }'
Then paste one of the prompts above: Muse Code finds Chatterbox TTS on Spiral, shows the price and runs it.
Chatterbox TTS providers and prices
Spiral runs Chatterbox TTS through fal. Open a card for today's price, with every fee included.
$0.0325 per 1,000 characters of text. Rounded up to the next 1,000 characters, minimum 1,000.
Settings you can ask for
Chatterbox TTS works from your audio URL. Ask Muse Code for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Exaggeration | 0 to 1 | 0.25 | Exaggeration factor for the generated speech (0.0 = no exaggeration, 1.0 = maximum exaggeration). |
| Temperature | 0.05 to 2 | 0.7 | Temperature for generation (higher = more creative). |
| CFG | 0.1 to 1 | 0.5 | |
| Seed | a whole number | Useful to control the reproducibility of the generated audio. Assuming all other properties didn't change, a fixed seed should always generate the exact same audio file. Set to 0 for random seed.. |
Every API field of Chatterbox · Text to Speech is on its tool page: open its card above.
What can you do with Chatterbox TTS in Muse Code?
Add spoken English walkthroughs, character dialogue, and narration to your project with Chatterbox TTS. Your coding agent can prepare scripts from project files and compare emotional intensity and pacing before you choose a recording.
Product tutorial narration
Turn an English walkthrough into spoken instructions. Generate each section separately so you can review the delivery alongside the corresponding screen recording.
Game character dialogue
Create short English character lines using a reference voice. Compare restrained and dramatic readings by adjusting emotional exaggeration.
Spoken assistant replies
Read an assistant's English response aloud. If the reference speaker sounds rushed, try lower guidance and review the pacing.
Narration in your voice
Use a short recording of your voice to narrate English introductions, explainers, or lesson passages without training a separate voice model.
Scheduled audio briefings
Have an agent draft a concise English update and turn it into speech. Reuse a reference recording and review how names and numbers sound.
Alternate voiceover readings
Generate several readings of the same English script. Compare emotional intensity and pacing before selecting audio for a video edit.
More on Chatterbox TTS and Muse Code
Overview
Chatterbox TTS in other agents
Questions about Chatterbox TTS in Muse Code
Can Muse Code use Chatterbox TTS?
Yes. Add Spiral to Muse Code as an MCP server, and Muse Code can find and run Chatterbox TTS like any built-in tool.
How much does Chatterbox TTS cost in Muse Code?
Each item in `text` adds $0.0325. 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 Chatterbox TTS in Muse Code?
No. Spiral runs Chatterbox TTS on its own fal account. You sign in to Spiral once and never paste a key.
How long does it take to set up Chatterbox 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 Chatterbox TTS runs?
Chatterbox TTS runs in the background. Muse Code starts the run, checks on it and gives you the audio when it's ready.
Does Chatterbox TTS support languages other than English?
The original Chatterbox TTS is documented as English. Chatterbox Multilingual provides broader language support, so its language list does not apply here.
How do I make the delivery more expressive?
Try emotional exaggeration around 0.7 and guidance around 0.3 as a starting point for dramatic speech. Listen before increasing intensity further, since extreme exaggeration can be unstable.
Why does a more expressive reading sound faster?
Higher exaggeration tends to speed up speech. Lowering guidance toward 0.3 can help restore a slower, more deliberate delivery.
Can I add laughter with bracketed tags?
Explicit vocal-reaction tags are documented for Chatterbox Turbo. For Chatterbox TTS, use the reference voice and emotional exaggeration controls instead of relying on those tags.
Does Chatterbox TTS watermark its audio?
Yes. Chatterbox includes PerTh watermarking in its generated audio.
Start using Chatterbox TTS 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 https://spiral.ai/SKILL.md


