How to Use Index TTS 2.0 in Gemini CLI
Index TTS 2.0 turns scripts into expressive speech with separate control over voice identity and emotion. Use it for character dialogue and narration when the same voice needs different deliveries.
Prompts to try with Index TTS 2.0 in Gemini CLI
Copy an example into Gemini CLI, or ask in your own words.
Use Index TTS 2.0 to narrate the project's onboarding script with the provided voice reference and a calm delivery.
Use Index TTS 2.0 to generate calm, angry, and sad takes of the first game dialogue line, keeping its voice reference fixed.
Use Index TTS 2.0 for the tutorial script, taking voice identity from the narrator recording and emotion from the performance reference.
Use Index TTS 2.0 to read the project's Chinese lesson examples. Keep each example separate for pronunciation review.
Use Index TTS 2.0 to narrate the demo script, then measure the audio duration before placing it on the video timeline.
How to set up Index TTS 2.0 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 Index TTS 2.0
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/index-tts-2/text-to-speech", "input": { "audio_url": "https://storage.googleapis.com/falserverless/example_inputs/index-tts-2/tts_in.mp3", "prompt": "Hide! He'\''s coming! He'\''s coming to get us!" } }'
Then paste one of the prompts above: Gemini CLI finds Index TTS 2.0 on Spiral, shows the price and runs it.
Index TTS 2.0 providers and prices
Spiral runs Index TTS 2.0 through fal. Open a card for today's price, with every fee included.
Settings you can ask for
Index TTS 2.0 works from your audio URL and prompt. Ask Gemini CLI for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Strength | 0 to 1 | 1 | The strength of the emotional style transfer. Higher values result in stronger emotional influence. |
| Should use prompt for emotion | on or off | off | Whether to use the |
Every API field of Index TTS 2.0 is on its tool page: open its card above.
What can you do with Index TTS 2.0 in Gemini CLI?
Create spoken dialogue and narration from scripts in your project with Index TTS 2.0. Your coding agent can prepare separate takes for each emotional direction and keep them organized for review.
Character dialogue
Give one character calm, angry, and sad readings while keeping the same voice reference.
Explainer narration
Turn an English explainer script into a calm spoken guide using a chosen voice reference.
Chinese lesson narration
Create spoken Chinese examples for lessons, then review pronunciation before publishing.
Dialogue rehearsal
Compare several emotional readings of a line before directing a recording session.
Performance-guided voiceovers
Use one recording for voice identity and another speaker's performance for emotional direction.
Recurring audio briefings
Read each day's prepared summary with the same voice reference and a calm delivery direction.
More on Index TTS 2.0 and Gemini CLI
Overview
Index TTS 2.0 in other agents
Questions about Index TTS 2.0 in Gemini CLI
Can Gemini CLI use Index TTS 2.0?
Yes. Add Spiral to Gemini CLI as an MCP server, and Gemini CLI can find and run Index TTS 2.0 like any built-in tool.
How much does Index TTS 2.0 cost in Gemini CLI?
Up to $0.156 per run at the default inputs for 60 seconds of input. 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 Index TTS 2.0 in Gemini CLI?
No. Spiral runs Index TTS 2.0 on its own fal account. You sign in to Spiral once and never paste a key.
How long does it take to set up Index TTS 2.0 in Gemini CLI?
About two minutes: add the server, then sign in, then check it.
Does Gemini CLI wait while Index TTS 2.0 runs?
Index TTS 2.0 runs in the background. Gemini CLI starts the run, checks on it and gives you the audio when it's ready.
What is Index TTS 2.0 useful for?
Use it for narration or character lines that need a recognizable voice with different emotional deliveries. You can guide emotion with a separate performance reference or a written description.
Can the voice and emotion references come from different people?
Yes. Index TTS 2.0 separates voice identity from emotional expression, so a second speaker's performance can guide the delivery.
How should I describe the emotion?
Give a specific delivery direction, such as calm reassurance or sadness after a disappointment. Keep that direction separate from the words you want spoken.
Which languages should I use?
Chinese and English are the documented languages in the training description. The Index TTS 2.0 paper reports training data in both.
Can I request an exact clip length?
Do not rely on an exact duration. Although the research demonstrates duration control, the maker's release notes say that capability was not enabled in the IndexTTS-2 public release.
Start using Index TTS 2.0 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


