How to Use Orpheus TTS in Gemini CLI
Orpheus TTS turns English scripts into expressive speech for narration and conversational replies. Inline cues such as <sigh> and <chuckle> add vocal reactions, while generation settings also affect speaking speed.
Prompts to try with Orpheus TTS in Gemini CLI
Copy an example into Gemini CLI, or ask in your own words.
Read the README and use Orpheus TTS to narrate a 60-word English overview of what the project does. Verify every statement against the repository and keep command syntax out of the spoken script.
Find the onboarding copy in this project. Use Orpheus TTS to create a short English welcome recording that explains the first task in plain language.
Use Orpheus TTS to audition this line from our dialogue prototype: 'I thought I had it figured out. <sigh> Let me try again.' Save the recording beside the scene assets.
Use Orpheus TTS to create two readings of the same 40-word English feature explanation from the changelog. Hold repetition_penalty at 1.2 and compare temperature 0.6 with 0.8; label the recordings for a listening review.
Read the empty-state messages in the project and select three that need spoken equivalents. Rewrite each as one clear English sentence, then generate a separate recording with Orpheus TTS.
How to set up Orpheus TTS in Gemini CLI
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the server
Or add it to ~/.gemini/settings.json yourself:
gemini mcp add --scope user --transport http spiral https://api.spiral.ai/mcp
- Sign in
Start gemini and run:
/mcp auth spiral
- Check it
In Gemini CLI, run /mcp. From your shell:
gemini mcp list
Use the Spiral skill
- Send Gemini CLI 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 Orpheus 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/orpheus-tts", "input": { "text": "I just found a hidden treasure in the backyard! <gasp> Check it out!" } }'
Then paste one of the prompts above: Gemini CLI finds Orpheus TTS on Spiral, shows the price and runs it.
Orpheus TTS providers and prices
Spiral runs Orpheus TTS through fal. Open a card for today's price, with every fee included.
$0.065 per 1,000 characters of text. Rounded up to the next 1,000 characters, minimum 1,000.
Settings you can ask for
Ask Gemini CLI for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Voice | tara, leah, jess, leo, dan, mia, zac, or zoe | tara | Voice ID for the desired voice. |
| Temperature | 0 to 2 | 0.7 | Temperature for generation (higher = more creative). |
| Repetition penalty | 1.1 to 2 | 1.2 | Repetition penalty (>= 1.1 required for stable generations). |
Every API field of Orpheus TTS is on its tool page: open its card above.
What can you do with Orpheus TTS in Gemini CLI?
Turn project documentation and interface copy into English narration with Orpheus TTS. A coding agent can prepare scripts from repository files and generate recordings for walkthroughs or dialogue prototypes.
Product walkthrough narration
Turn a short English walkthrough script into a spoken explanation of one task, such as creating a report or finding a saved search.
Story excerpt readings
Generate a spoken reading of an English story excerpt. Try a documented vocal cue where a character laughs, sighs, or gasps.
Conversational assistant replies
Give short English assistant responses a spoken delivery, from answering a question to explaining a failed action.
Audio learning summaries
Convert a concise lesson recap into English speech for listening practice or review away from a screen.
Recurring spoken briefings
Have an agent prepare a short English update from verified information, then generate a recording for the daily or weekly briefing.
Dialogue auditions
Render short dialogue lines separately to compare phrasing and vocal reactions before choosing a reading for a scene or prototype.
More on Orpheus TTS and Gemini CLI
Overview
Orpheus TTS in other agents
Questions about Orpheus TTS in Gemini CLI
Can Gemini CLI use Orpheus TTS?
Yes. Add Spiral to Gemini CLI as an MCP server, and Gemini CLI can find and run Orpheus TTS like any built-in tool.
How much does Orpheus TTS cost in Gemini CLI?
Each item in `text` adds $0.065. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Gemini CLI plan is separate.
Do I need a fal account to use Orpheus TTS in Gemini CLI?
No. Spiral runs Orpheus 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 Orpheus TTS in Gemini CLI?
About two minutes: add the server, then sign in, then check it.
Does Gemini CLI wait while Orpheus TTS runs?
Orpheus TTS runs in the background. Gemini CLI starts the run, checks on it and gives you the audio when it's ready.
What is Orpheus TTS good at?
Orpheus TTS suits English narration and conversational replies where phrasing and vocal expression matter. Useful starting points include spoken explainers, story excerpts, and assistant responses.
Which language should I use with Orpheus TTS?
Use English for the original Orpheus TTS release. Canopy Labs documents its multilingual releases separately, so their language coverage should not be assumed here.
How do I add laughter or a sigh?
Insert a supported cue directly into the spoken script, such as 'Well, that went differently. <sigh> Let's try again.' Documented cues include <laugh>, <chuckle>, <sigh>, <cough>, <sniffle>, <groan>, <yawn>, and <gasp>.
Can I reliably command an exact emotion?
Treat broad emotion labels cautiously: a Canopy collaborator said they did not work on the original released finetune. Use the documented vocal cues for specific reactions, and audition the result before relying on a particular emotional reading.
Which settings affect speaking speed?
Canopy documents that increasing temperature and repetition penalty makes speech faster. Change one setting at a time and compare the same script; keep repetition penalty at or above 1.1 for stability.
Start using Orpheus TTS in Gemini CLI
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Gemini CLI:
set up https://spiral.ai/SKILL.md


