How to Use ElevenLabs Multilingual v2 in Gemini CLI
ElevenLabs Multilingual v2 turns scripts into consistent narration for audiobooks, lessons, and video voiceovers in 29 languages. Its strength is long-form delivery, with up to 10,000 characters per generation.
Prompts to try with ElevenLabs Multilingual v2 in Gemini CLI
Copy an example into Gemini CLI, or ask in your own words.
Read the project's getting-started guide and write a 250-word onboarding narration. Generate it with ElevenLabs Multilingual v2, using 50% stability and no style exaggeration.
Use the latest changelog entry to write a spoken release briefing explaining the three most useful changes. Generate the narration with ElevenLabs Multilingual v2 and keep the script below 3,000 characters.
Find the English, Spanish, and French onboarding copy in the repository. Prepare a separate narration script for each language and generate each with ElevenLabs Multilingual v2.
Read the tutorial scripts in this project and generate narration with ElevenLabs Multilingual v2. Divide any script over 10,000 characters at paragraph boundaries and keep the same voice throughout.
Take the first paragraph of the project's demo script and generate two readings with ElevenLabs Multilingual v2. Use 40% stability for one and 65% for the other, keeping similarity at 75% and style exaggeration off.
How to set up ElevenLabs Multilingual v2 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 ElevenLabs Multilingual v2
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/elevenlabs/tts/multilingual-v2", "input": { "text": "Hello! This is a test of the text to speech system, powered by ElevenLabs. How does it sound?" } }'
Then paste one of the prompts above: Gemini CLI finds ElevenLabs Multilingual v2 on Spiral, shows the price and runs it.
ElevenLabs Multilingual v2 providers and prices
Spiral runs ElevenLabs Multilingual v2 through fal. Open a card for today's price, with every fee included.
$0.13 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 |
|---|---|---|---|
| Stability | 0 to 1 | 0.5 | Voice stability (0-1) |
| Similarity boost | 0 to 1 | 0.75 | Similarity boost (0-1) |
| Style | 0 to 1 | 0 | Style exaggeration (0-1) |
| Speed | 0.7 to 1.2 | 1 | Speech speed (0.7-1.2). Values below 1.0 slow down the speech, above 1.0 speed it up. Extreme values may affect quality. |
| Timestamps | on or off | off | Whether to return timestamps for each word in the generated speech |
| Apply text normalization | auto, on, or off | auto | This parameter controls text normalization with three modes: 'auto', 'on', and 'off'. When set to 'auto', the system will automatically decide whether to apply text normalization (e.g., spelling out numbers). With 'on', text normalization will always be applied, while with 'off', it will be skipped. |
Every API field of ElevenLabs TTS Multilingual v2 is on its tool page: open its card above.
What can you do with ElevenLabs Multilingual v2 in Gemini CLI?
Turn project documentation into spoken tutorials, release briefings, and training narration. Your coding agent can prepare scripts from repository files and divide long passages into separate generations.
Audiobook narration
Turn book chapters into spoken sections with a consistent narrator. Split chapters that exceed 10,000 characters.
Employee training
Narrate onboarding lessons, policy explanations, and process walkthroughs. Start with moderate stability and no style exaggeration.
Product explainer voiceovers
Create narration for product demonstrations and explainer videos. Generate each scene separately so revisions stay focused.
Localized video narration
Generate separate voiceovers from translated scripts in supported languages, including Spanish, French, German, and Japanese.
Audio editions of articles
Make spoken editions of essays, documentation, and educational articles for readers who prefer listening.
Language lesson narration
Read lesson scripts in supported languages. Add short pauses between an example sentence and its explanation.
Narrated release notes
Convert written product updates into a spoken briefing that explains changes and their practical effects.
More on ElevenLabs Multilingual v2 and Gemini CLI
Overview
ElevenLabs Multilingual v2 in other agents
Questions about ElevenLabs Multilingual v2 in Gemini CLI
Can Gemini CLI use ElevenLabs Multilingual v2?
Yes. Add Spiral to Gemini CLI as an MCP server, and Gemini CLI can find and run ElevenLabs Multilingual v2 like any built-in tool.
How much does ElevenLabs Multilingual v2 cost in Gemini CLI?
Each item in `text` adds $0.13. 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 ElevenLabs Multilingual v2 in Gemini CLI?
No. Spiral runs ElevenLabs Multilingual v2 on its own fal account. You sign in to Spiral once and never paste a key.
How long does it take to set up ElevenLabs Multilingual v2 in Gemini CLI?
About two minutes: add the server, then sign in, then check it.
Does Gemini CLI wait while ElevenLabs Multilingual v2 runs?
ElevenLabs Multilingual v2 runs in the background. Gemini CLI starts the run, checks on it and gives you the audio when it's ready.
What is ElevenLabs Multilingual v2 best for?
Audiobooks, instructional narration, and video voiceovers are strong fits. ElevenLabs highlights consistent delivery across long passages.
Which languages does ElevenLabs Multilingual v2 support?
It supports 29 languages, including English, Spanish, French, German, Japanese, Chinese, Hindi, and Arabic.
How much text can ElevenLabs Multilingual v2 read at once?
The documented limit is 10,000 characters per generation. For longer scripts, generate separate sections.
How do I make the delivery more expressive?
Lower stability to allow more emotional variation. Raise it for steadier narration, but avoid pushing it so high that the voice sounds monotonous.
How do I add a pause?
Insert a break tag such as <break time="1.0s" /> in the script. Supported pauses can last up to three seconds.
Start using ElevenLabs Multilingual v2 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


