[Integrations](https://spiral.ai/integrations) › [Gemini CLI](https://spiral.ai/integrations/gemini-cli) › [ElevenLabs model catalog](https://spiral.ai/integrations/gemini-cli/elevenlabs-model-catalog)

# How to Use ElevenLabs model catalog in Gemini CLI

Returns documented models with IDs, capabilities, languages, limits, and deprecation information. Use it to compare candidates before reading detailed model guidance.

|  |  |
| --- | --- |
| Model | ElevenLabs model catalog |
| Available through | Alexandria |
| Category | Developer |
| Price | $0.00873 per call. |
| Returns | json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with ElevenLabs model catalog in Gemini CLI

- Use ElevenLabs model catalog to compare eleven_flash_v2_5 and eleven_multilingual_v2 for this project's Spanish narration feature. Check documented language coverage and length limits.
- Use ElevenLabs model catalog to look this up and give me the result as a table. Save the result in ./assets.
- Pull the latest numbers from ElevenLabs model catalog and tell me what changed since last week.
- Check ElevenLabs model catalog and summarize what you find in three bullet points.
- Pull the newest data from ElevenLabs model catalog and give me the result as a table.

## How to set up ElevenLabs model catalog in Gemini CLI

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

### Use Spiral's MCP server

1. **Add the server**: Or add it to `~/.gemini/settings.json` yourself:

```bash
gemini mcp add --scope user --transport http spiral https://api.spiral.ai/mcp
```

2. **Sign in**: Start `gemini` and run:

```text
/mcp auth spiral
```

3. **Check it**: In Gemini CLI, run `/mcp`. From your shell:

```bash
gemini mcp list
```

### Use the Spiral skill

1. **Send Gemini CLI 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 ElevenLabs model catalog**: 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": "alexandria",
    "model": "elevenlabs-io/developer-docs/list_models",
    "input": {
      "q": "<q>"
    }
  }'
```

Then paste one of the prompts above: Gemini CLI finds ElevenLabs model catalog on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/gemini-cli

## ElevenLabs model catalog tools and prices

- [ElevenLabs · List models](https://spiral.ai/tools/alexandria/elevenlabs-io/developer-docs/list_models) (Alexandria): $0.00873 per call.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| q |  | — | Substring of the model id or description, e.g. `flash› or `speech recognition›. |
| include_deprecated |  | — | Include deprecated models (default true). |

## What can you do with ElevenLabs model catalog in Gemini CLI?

Produce an implementation review for an ElevenLabs audio feature using official references and product explanations. A coding agent can compare that evidence with the project's speech adapter, model choices, and developer notes.

### Review a speech synthesis implementation

Check a proposed narration workflow against the Create speech reference, model guidance, support explanations, and plan feature comparisons. Turn the relevant documentation into a concrete implementation checklist.

### Scope Spanish and Japanese audiobook narration

Compare documented language support, narration guidance, and feature availability for a bilingual audiobook. Read the relevant product posts and help articles before recommending a model and production approach.

### Prepare a model migration review

Investigate a move from an older ElevenLabs model by comparing replacement guidance, dated changes, API references, launch explanations, and feature availability. Produce a review that separates required implementation changes from optional improvements.

### Fact-check an ElevenLabs technical article

Verify claims about supported languages, model limits, available features, and API behavior against official material. Use launch posts and dated changes to check historical claims, then cite the specific reference or help page behind each technical statement.

### Write a weekly audio technology brief

Collect ElevenLabs announcements and changelog entries, then read the model documentation behind relevant releases. Explain which developments matter for narration, transcription, or conversational audio experiments.

## Overview

- [Alexandria](https://spiral.ai/providers/alexandria)
- [All Gemini CLI guides](https://spiral.ai/integrations/gemini-cli)

## ElevenLabs model catalog in other agents

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

## More Gemini CLI guides

- [ElevenLabs help article](https://spiral.ai/integrations/gemini-cli/elevenlabs-help-article)
- [ElevenLabs model details](https://spiral.ai/integrations/gemini-cli/elevenlabs-model-details)
- [ElevenLabs documentation search](https://spiral.ai/integrations/gemini-cli/elevenlabs-documentation-search)
- [ElevenLabs plan comparison](https://spiral.ai/integrations/gemini-cli/elevenlabs-plan-comparison)
- [ElevenLabs documentation page](https://spiral.ai/integrations/gemini-cli/elevenlabs-documentation-page)
- [Grok Bot and Build release notes](https://spiral.ai/integrations/gemini-cli/grok-bot-and-build-release-notes)

## Questions about ElevenLabs model catalog in Gemini CLI

**Can Gemini CLI use ElevenLabs model catalog?**

Yes. Add Spiral to Gemini CLI as an MCP server, and Gemini CLI can find and run ElevenLabs model catalog like any built-in tool.

**How much does ElevenLabs model catalog cost in Gemini CLI?**

$0.00873 per call. 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 an Alexandria account to use ElevenLabs model catalog in Gemini CLI?**

No. Spiral runs ElevenLabs model catalog on its own Alexandria account. You sign in to Spiral once and never paste a key.

**How long does it take to set up ElevenLabs model catalog in Gemini CLI?**

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

**Does Gemini CLI wait while ElevenLabs model catalog runs?**

ElevenLabs model catalog runs in the background. Gemini CLI starts the run, checks on it and gives you the json when it's ready.

**What public material does this source cover?**

It covers public ElevenLabs documentation, blog posts, comparison pages, and help content from elevenlabs.io and help.elevenlabs.io. The provider identifies documentation indexes, Markdown pages, structured website data, and the public help center API as its sources.

**Which ElevenLabs products does the documentation cover?**

The documentation covers text-to-speech, speech-to-text, voice cloning, voice agents, and generative audio. ElevenLabs publishes separate subject indexes for guides and API references.

**Can an older ElevenLabs article have been updated?**

Yes. The Voice Conversion article shows a publication date of September 6, 2022, and a last-updated date of November 3, 2026, so its original publication date alone does not describe the age of its text.

**Does ElevenLabs document one language count for every model?**

No. Its language-support article documents 70+ languages for Eleven v3 and 29 for Multilingual v2, so language coverage needs to be checked against the named model.

**Are the published model latency figures end-to-end measurements?**

The figures marked with the dagger footnote in the models guide are medians that exclude application and network latency. They do not measure the complete delay a user experiences.

