[Integrations](https://spiral.ai/integrations) › [Claude Code](https://spiral.ai/integrations/claude-code) › [Gemini 2.5 Pro Preview TTS](https://spiral.ai/integrations/claude-code/gemini-2-5-pro-preview-tts)

# How to Use Gemini 2.5 Pro Preview TTS in Claude Code

Gemini 2.5 Pro Preview TTS turns scripts into expressive narration and two-person dialogue. Google positions it for speech quality and complex prompts, while Gemini 2.5 Flash Preview TTS emphasizes low latency.

|  |  |
| --- | --- |
| Model | Gemini 2.5 Pro Preview TTS |
| Available through | Gemini |
| Category | Audio |
| Price | Input text: $1.30 per 1M tokens. Output speech: $26.00 per 1M audio tokens. |
| Returns | audio |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Gemini 2.5 Pro Preview TTS in Claude Code

- Read the project's onboarding docs and draft a 150-word walkthrough. Use Gemini 2.5 Pro Preview TTS to narrate it as a patient instructor at a measured pace.
- Turn the latest changelog into a short spoken release summary. Use Gemini 2.5 Pro Preview TTS with a factual tone and clear emphasis on changes users will notice.
- Find a two-character scene in the game's dialogue files. Use Gemini 2.5 Pro Preview TTS to perform a short excerpt with one cautious character and one confident character.
- Take one lesson from the project's training content. Use Gemini 2.5 Pro Preview TTS to make a narration sample that slows down around the instructions.
- Prepare one short narration script from the README. Use Gemini 2.5 Pro Preview TTS to record it twice, once conversationally and once as a formal technical presentation.

## How to set up Gemini 2.5 Pro Preview TTS in Claude Code

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

### Use Spiral's MCP server

1. **Add the hosted server**: This adds Spiral to the current project. Add `--scope user` to use it in every project.

```bash
claude mcp add --transport http spiral https://api.spiral.ai/mcp
```

2. **Sign in**: Start `claude`, type `/mcp`, choose spiral and Authenticate. Sign in to Spiral in the browser and click Authorize. No API key.

### Use the Spiral skill

1. **Send Claude 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 Gemini 2.5 Pro Preview 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": "gemini",
    "model": "gemini-2.5-pro-preview-tts",
    "input": {
      "contents": [
        {}
      ]
    }
  }'
```

Then paste one of the prompts above: Claude Code finds Gemini 2.5 Pro Preview TTS on Spiral, shows the price and runs it.

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

## Gemini 2.5 Pro Preview TTS tools and prices

- [Gemini 2.5 Pro Preview TTS](https://spiral.ai/tools/gemini/gemini-2.5-pro-preview-tts) (Gemini): Input text: $1.30 per 1M tokens. Output speech: $26.00 per 1M audio tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| generationConfig |  | — | Configuration options for model generation and outputs. |

## What can you do with Gemini 2.5 Pro Preview TTS in Claude Code?

Create spoken walkthroughs, narration, and character dialogue from your project's written content. Let the coding agent prepare the script, then use Gemini 2.5 Pro TTS to perform it with explicit delivery directions.

### Audiobook passages

Record a finished chapter section with deliberate pacing and emotional direction. Generate long manuscripts section by section.

### Two-person podcast explainers

Turn an approved host-and-guest script into dialogue, with a distinct delivery brief for each speaker.

### Product tutorial narration

Read walkthrough scripts in a patient instructional tone, slowing down around steps that need extra attention.

### Localized training audio

Generate spoken versions of approved translations. Preview a short lesson in each target language before recording the rest.

### Game dialogue prototypes

Try character lines with different emotional directions, or rehearse a scripted exchange between two characters.

### Spoken news briefings

Read a fact-checked briefing with measured delivery and clear emphasis on the main developments.

### Poetry readings

Explore how pace, emotion, and accent change the performance of a finished poem.

## Overview

- [Google Gemini](https://spiral.ai/providers/gemini)
- [All Claude Code guides](https://spiral.ai/integrations/claude-code)

## Gemini 2.5 Pro Preview TTS in other agents

- [Amp](https://spiral.ai/integrations/amp/gemini-2-5-pro-preview-tts)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/gemini-2-5-pro-preview-tts)
- [Claude](https://spiral.ai/integrations/claude-desktop/gemini-2-5-pro-preview-tts)
- [Cline](https://spiral.ai/integrations/cline/gemini-2-5-pro-preview-tts)
- [Codex](https://spiral.ai/integrations/codex/gemini-2-5-pro-preview-tts)
- [Cursor](https://spiral.ai/integrations/cursor/gemini-2-5-pro-preview-tts)
- [Devin](https://spiral.ai/integrations/devin/gemini-2-5-pro-preview-tts)
- [dots](https://spiral.ai/integrations/dots/gemini-2-5-pro-preview-tts)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/gemini-2-5-pro-preview-tts)
- [Gemini](https://spiral.ai/integrations/gemini/gemini-2-5-pro-preview-tts)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/gemini-2-5-pro-preview-tts)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/gemini-2-5-pro-preview-tts)
- [goose](https://spiral.ai/integrations/goose/gemini-2-5-pro-preview-tts)
- [Grok](https://spiral.ai/integrations/grok/gemini-2-5-pro-preview-tts)
- [Grok Build](https://spiral.ai/integrations/grok-build/gemini-2-5-pro-preview-tts)
- [Hermes](https://spiral.ai/integrations/hermes/gemini-2-5-pro-preview-tts)
- [Instinct](https://spiral.ai/integrations/instinct/gemini-2-5-pro-preview-tts)
- [Manus](https://spiral.ai/integrations/manus/gemini-2-5-pro-preview-tts)
- [Muse](https://spiral.ai/integrations/muse/gemini-2-5-pro-preview-tts)
- [Muse Code](https://spiral.ai/integrations/muse-code/gemini-2-5-pro-preview-tts)
- [n8n](https://spiral.ai/integrations/n8n/gemini-2-5-pro-preview-tts)
- [Notion](https://spiral.ai/integrations/notion/gemini-2-5-pro-preview-tts)
- [OpenClaw](https://spiral.ai/integrations/openclaw/gemini-2-5-pro-preview-tts)
- [opencode](https://spiral.ai/integrations/opencode/gemini-2-5-pro-preview-tts)
- [Perplexity](https://spiral.ai/integrations/perplexity/gemini-2-5-pro-preview-tts)
- [Raycast](https://spiral.ai/integrations/raycast/gemini-2-5-pro-preview-tts)
- [VS Code](https://spiral.ai/integrations/vscode/gemini-2-5-pro-preview-tts)
- [Windsurf](https://spiral.ai/integrations/windsurf/gemini-2-5-pro-preview-tts)
- [Zapier](https://spiral.ai/integrations/zapier/gemini-2-5-pro-preview-tts)

## More Claude Code guides

- [Gemini 2.5 Flash TTS](https://spiral.ai/integrations/claude-code/gemini-2-5-flash-tts)
- [Gemini 3.1 Flash TTS](https://spiral.ai/integrations/claude-code/gemini-3-1-flash-tts)
- [GPT-4o mini Transcribe](https://spiral.ai/integrations/claude-code/gpt-4o-mini-transcribe)
- [Gemini 3.8 Flash TTS](https://spiral.ai/integrations/claude-code/gemini-3-8-flash-tts)
- [GPT-4o mini TTS](https://spiral.ai/integrations/claude-code/gpt-4o-mini-tts)
- [Gemini 3.8 Flash-Lite TTS](https://spiral.ai/integrations/claude-code/gemini-3-8-flash-lite-tts)

## Questions about Gemini 2.5 Pro Preview TTS in Claude Code

**Can Claude Code use Gemini 2.5 Pro Preview TTS?**

Yes. Add Spiral to Claude Code as an MCP server, and Claude Code can find and run Gemini 2.5 Pro Preview TTS like any built-in tool.

**How much does Gemini 2.5 Pro Preview TTS cost in Claude Code?**

Input text: $1.30 per 1M tokens. Output speech: $26.00 per 1M audio tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Claude Code plan is separate.

**Do I need a Gemini account to use Gemini 2.5 Pro Preview TTS in Claude Code?**

No. Spiral runs Gemini 2.5 Pro Preview TTS on its own Gemini account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Gemini 2.5 Pro Preview TTS in Claude Code?**

About two minutes: add the hosted server, then sign in.

**Does Claude Code wait while Gemini 2.5 Pro Preview TTS runs?**

Gemini 2.5 Pro Preview TTS runs in the background. Claude Code starts the run, checks on it and gives you the audio when it's ready.

**What is Gemini 2.5 Pro TTS best at?**

Use it for narration and dialogue where delivery matters: audiobook passages, podcast scripts, and spoken tutorials. Google positions Pro for quality and complex creative speech workflows.

**Can Gemini 2.5 Pro TTS generate two different speakers?**

Yes. It can turn text into a two-person audio overview, making it useful for scripted interviews, question-and-answer lessons, and podcast conversations.

**How much text and audio can Gemini 2.5 Pro TTS handle?**

Google lists an input limit of 8,192 tokens and an output limit of 16,384 tokens. Treat those as token limits rather than a guaranteed recording length; split long scripts into sections.

**Which languages does Gemini 2.5 Pro TTS support?**

Google's Gemini 2.5 technical report describes more than 80 languages for Preview TTS Pro and Flash. Test a short passage in your target language before generating a full recording.

**How should I describe the voice delivery?**

Specify the role, tone, accent, and pace in ordinary language, such as a patient instructor explaining one step at a time. Google recommends specific style prompts and warns that unfamiliar tags may be spoken aloud.

