[Integrations](https://spiral.ai/integrations) › [Google Antigravity](https://spiral.ai/integrations/antigravity) › [Voxtral Small 24B](https://spiral.ai/integrations/antigravity/voxtral-small-24b)

# How to Use Voxtral Small 24B in Google Antigravity

Use Voxtral Small 24B for speech transcription, translation, and questions about recordings. Its 32k context supports up to 30 minutes of transcription or 40 minutes of audio understanding.

|  |  |
| --- | --- |
| Model | Voxtral Small 24B |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.006148 per run at the default inputs. $0.13 per 1M input tokens, $130.00 per 1M audio input tokens, $0.39 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Voxtral Small 24B in Google Antigravity

- Use Voxtral Small 24B to summarize recordings/planning.mp3 into requirements. Compare them with README.md and list questions before proposing code changes.
- Use Voxtral Small 24B to transcribe recordings/bug-report.wav, which is under 30 minutes. Preserve spoken error messages and mark unclear wording.
- Use Voxtral Small 24B to extract acceptance criteria from recordings/demo-feedback.mp3. Compare them with the project's existing tests and report gaps.
- Use Voxtral Small 24B to summarize recordings/design-review.mp3 into decisions and open questions. Draft a Markdown note for the project's docs directory.
- Use Voxtral Small 24B to translate recordings/customer-feedback-es.mp3 into English. List reported behavior separately from your suggested investigation steps.

## How to set up Voxtral Small 24B in Google Antigravity

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

### Use Spiral's MCP server

1. **Open the MCP config**: * Antigravity App: click Customizations, then Installed. In the MCP Servers section, click Copy Config File Path and open that file. * Antigravity IDE: click … at the top of the agent side panel, select MCP Servers, then Manage MCP Servers › View raw config. * Antigravity CLI: edit `~/.gemini/config/mcp_config.json`.

2. **Add the server**: Add Spiral under `mcpServers`:

```json
{
  "mcpServers": {
    "spiral": {
      "serverUrl": "https://api.spiral.ai/mcp"
    }
  }
}
```

3. **Sign in**: In the Antigravity App, open Customizations › Installed. Under MCP Servers, click Authenticate next to Spiral. Sign in to Spiral, pick the organization and click Authorize. Copy the authorization code the browser shows, paste it into Enter authorization code and click Submit. No API key.

### Use the Spiral skill

1. **Send Google Antigravity 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 Voxtral Small 24B**: 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": "openrouter",
    "model": "mistralai/voxtral-small-24b-2507",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: Google Antigravity finds Voxtral Small 24B on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/antigravity

## Voxtral Small 24B tools and prices

- [Mistral: Voxtral Small 24B 2507](https://spiral.ai/tools/openrouter/mistralai/voxtral-small-24b-2507) (OpenRouter): Up to $0.006148 per run at the default inputs. $0.13 per 1M input tokens, $130.00 per 1M audio input tokens, $0.39 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| seed |  | — |  |
| stop |  | — |  |
| tools |  | — |  |
| top_p | 0 to 1 | — |  |
| max_tokens | 1 to 26214 | — | The most output tokens to generate. |
| temperature | 0 to 2 | — |  |

## What can you do with Voxtral Small 24B in Google Antigravity?

Turn spoken requirements into written implementation notes with Voxtral Small 24B. Ask your coding agent to compare those notes with project files before proposing changes.

### Meeting decision notes

Summarize a meeting recording into decisions, assigned actions, and unresolved questions. Request names and deadlines only when explicitly stated.

### Interview transcripts

Turn a recorded interview of up to 30 minutes into a transcript for editorial review.

### Translated interview excerpts

Translate a Spanish, French, German, or Italian interview excerpt into English text for an editor.

### Support call summaries

Extract the customer's problem, troubleshooting attempted, and agreed next step from a recorded support call.

### Lecture study notes

Summarize a lecture segment, then ask questions about the explanation and examples it contains.

### Podcast research

Pull an episode segment's main arguments and supporting examples into a research brief.

### Spoken product feedback

Turn a recorded user interview into reported problems, requested changes, and follow-up questions.

## Overview

- [OpenRouter](https://spiral.ai/providers/openrouter)
- [All Google Antigravity guides](https://spiral.ai/integrations/antigravity)

## Voxtral Small 24B in other agents

- [Amp](https://spiral.ai/integrations/amp/voxtral-small-24b)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/voxtral-small-24b)
- [Claude](https://spiral.ai/integrations/claude-desktop/voxtral-small-24b)
- [Claude Code](https://spiral.ai/integrations/claude-code/voxtral-small-24b)
- [Cline](https://spiral.ai/integrations/cline/voxtral-small-24b)
- [Codex](https://spiral.ai/integrations/codex/voxtral-small-24b)
- [Cursor](https://spiral.ai/integrations/cursor/voxtral-small-24b)
- [Devin](https://spiral.ai/integrations/devin/voxtral-small-24b)
- [dots](https://spiral.ai/integrations/dots/voxtral-small-24b)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/voxtral-small-24b)
- [Gemini](https://spiral.ai/integrations/gemini/voxtral-small-24b)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/voxtral-small-24b)
- [goose](https://spiral.ai/integrations/goose/voxtral-small-24b)
- [Grok](https://spiral.ai/integrations/grok/voxtral-small-24b)
- [Grok Build](https://spiral.ai/integrations/grok-build/voxtral-small-24b)
- [Hermes](https://spiral.ai/integrations/hermes/voxtral-small-24b)
- [Instinct](https://spiral.ai/integrations/instinct/voxtral-small-24b)
- [Manus](https://spiral.ai/integrations/manus/voxtral-small-24b)
- [Muse](https://spiral.ai/integrations/muse/voxtral-small-24b)
- [Muse Code](https://spiral.ai/integrations/muse-code/voxtral-small-24b)
- [n8n](https://spiral.ai/integrations/n8n/voxtral-small-24b)
- [Notion](https://spiral.ai/integrations/notion/voxtral-small-24b)
- [OpenClaw](https://spiral.ai/integrations/openclaw/voxtral-small-24b)
- [opencode](https://spiral.ai/integrations/opencode/voxtral-small-24b)
- [Perplexity](https://spiral.ai/integrations/perplexity/voxtral-small-24b)
- [Raycast](https://spiral.ai/integrations/raycast/voxtral-small-24b)
- [VS Code](https://spiral.ai/integrations/vscode/voxtral-small-24b)
- [Windsurf](https://spiral.ai/integrations/windsurf/voxtral-small-24b)
- [Zapier](https://spiral.ai/integrations/zapier/voxtral-small-24b)

## More Google Antigravity guides

- [Venice Uncensored](https://spiral.ai/integrations/antigravity/venice-uncensored)
- [Weaver Alpha](https://spiral.ai/integrations/antigravity/weaver-alpha)
- [UnslopNemo 12B](https://spiral.ai/integrations/antigravity/unslopnemo-12b)
- [gpt-oss-20b](https://spiral.ai/integrations/antigravity/gpt-oss-20b)
- [UI-TARS 1.5 7B](https://spiral.ai/integrations/antigravity/ui-tars-1-5-7b)
- [o3](https://spiral.ai/integrations/antigravity/o3)

## Questions about Voxtral Small 24B in Google Antigravity

**Can Google Antigravity use Voxtral Small 24B?**

Yes. Add Spiral to Google Antigravity as an MCP server, and Google Antigravity can find and run Voxtral Small 24B like any built-in tool.

**How much does Voxtral Small 24B cost in Google Antigravity?**

Up to $0.006148 per run at the default inputs. $0.13 per 1M input tokens, $130.00 per 1M audio input tokens, $0.39 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Google Antigravity plan is separate.

**Do I need an OpenRouter account to use Voxtral Small 24B in Google Antigravity?**

No. Spiral runs Voxtral Small 24B on its own OpenRouter account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Voxtral Small 24B in Google Antigravity?**

About two minutes: open the MCP config, then add the server, then sign in.

**Does Google Antigravity wait while Voxtral Small 24B runs?**

Voxtral Small 24B runs in the background. Google Antigravity starts the run, checks on it and gives you the text, json when it's ready.

**What is Voxtral Small 24B useful for?**

Transcribing speech, translating spoken content, summarizing recordings, and answering questions about what was said. Use a focused question when you need a particular detail from a recording.

**How long can a recording be?**

Mistral documents up to 30 minutes for transcription and 40 minutes for audio understanding, with a 32k token context window. Split longer recordings into shorter sections before requesting a combined summary.

**Which languages does Voxtral Small 24B support?**

Mistral lists English, Spanish, French, Portuguese, Hindi, German, Dutch, and Italian. Specify whether you want the original language preserved or the content translated.

**Can Voxtral Small 24B generate a spoken reply?**

It produces text from audio or text input. Choose it for transcripts and written answers; speech generation requires a separate text-to-speech model.

**What sampling settings should I start with?**

Mistral recommends temperature 0.2 and top-p 0.95 for audio understanding. For transcription, its recommendation is temperature 0.

