# ElevenLabs MCP

> ElevenLabs gives your agent full control over AI speech generation, allowing you to create high-fidelity, lifelike voiceovers and dub videos into multiple languages. Manage voices, track usage quotas, and generate complex audio pipelines—all without leaving your chat interface.

## Overview
- **Category:** ai-frontier
- **Price:** Free
- **Tags:** text-to-speech, voice-synthesis, audio-generation, dubbing, speech-api, natural-language

## Description

This MCP lets you take the complexity out of professional audio production. Instead of jumping between separate platforms for scripting, recording, and localization, you talk to your agent and it handles the heavy lifting. You can convert raw text into perfect speech using lifelike voices or clone existing ones. If you're working on global content, you don't have to manually manage translation queues; you just tell your agent to dub a video into Spanish or French, and the system initiates the process automatically. Need to know how much budget you have left? You check your usage quota right in the chat. All this power is exposed through Vinkius, giving any MCP-compatible client full access to advanced audio tools that used to require dedicated API coding.

## Tools

### list_voices
Retrieves a list of all voice profiles available for use in your audio generation projects.

### list_pronunciation_dictionaries
Shows pre-made dictionaries that help guide the accurate pronunciation of specific words.

### get_voice
Pulls detailed information about a single voice profile, including its technical parameters.

### text_to_speech
Converts any block of text into audio and provides associated metadata for the job.

### list_models
Lists all available AI speech models, letting you choose the best engine for your specific task.

### list_history
Fetches a list of past audio generation jobs so you can review what was created and when.

### get_history_item
Retrieves the full details for one specific job from your history, including download links.

### get_user_info
Gathers general information about your connected ElevenLabs user profile.

### get_subscription
Checks your current subscription plan and remaining character usage limits.

### list_projects
Lists all ongoing or completed dubbing and voice projects you've initiated in the system.

## Prompt Examples

**Prompt:** 
```
Generate audio for: 'Hello, this is a lifelike AI voice.' using voice 'abc-123'
```

**Response:** 
```
Inference pipeline triggered! I've sent your script to ElevenLabs using voice 'abc-123'. The audio is being generated with perfect intonation. Would you like to check the history for the download link?
```

**Prompt:** 
```
Show me my remaining character quota
```

**Response:** 
```
Retrieving subscription info... You have used 15,000 characters out of your 100,000 monthly limit. You have 85,000 characters remaining for this billing cycle.
```

**Prompt:** 
```
Dub this video into Spanish: https://example.com/video.mp4
```

**Response:** 
```
Dubbing job initiated! I've started the translation queue for your video into Spanish. I'll provide the tracking ID (dub_abc) so you can monitor the rendering status.
```

## Capabilities

### Generate synthetic speech
Converts written text into high-quality spoken audio using various voices and intonations.

### Manage voice profiles
Browse, retrieve details on, and select from a global library of standard or cloned voices.

### Automate multi-language dubbing
Takes existing videos or audio and automatically creates translated versions in dozens of languages.

### Monitor usage and billing
Checks your current subscription limits, available character quotas, and past generation history.

### Structure complex speech tasks
Handles detailed audio synthesis jobs by sending specific parameters to the engine for precise control.

## Use Cases

### Launching a Global Product Line
A product manager needs to launch the same training video across five countries. Instead of hiring five separate voice actors, they ask their agent to initiate dubbing jobs for all five languages in one go using `list_projects` and `text_to_speech`. This ensures brand consistency and saves weeks of coordination.

### Updating a Technical Manual
A technical writer needs to update speech narration for an existing manual. They first use `list_voices` to select the corporate voice, then run small text segments through `text_to_speech`, and finally compare them against the previous version using `get_history_item`.

### Building a Media Pipeline
A developer needs to build an automated video generation tool. They connect this MCP, allowing their agent to automatically validate voice settings via `get_voice` and then use the results to feed into a larger system.

### Auditing Content Spend
A marketing director needs to track which campaigns are eating up the most budget. They ask their agent to call `list_history`, instantly generating a report on character usage across all departments for easy cost analysis.

## Benefits

- You get immediate control over voice assets. Instead of guessing which voices work best, you can use the `list_voices` tool to browse and select from a massive library before generating anything.
- Localization becomes trivial. If you need to dub a marketing video into five different languages, your agent handles it with one prompt, managing the entire translation queue for you.
- Quota management is simple. You never run out of budget because you can check your spending limits anytime using `get_subscription`, making content creation predictable.
- Debugging speech becomes easy. If a script has weird pronunciation or missing details, you use `list_pronunciation_dictionaries` to correct it before the audio generation even starts.
- Every job is logged. You can review your work and troubleshoot by calling `list_history`, ensuring nothing gets lost in manual spreadsheets or forgotten folders.

## How It Works

The bottom line is that your agent handles all the API calls and complexity; you just talk to it.

1. First, subscribe to this MCP and provide your ElevenLabs API Key to connect your account.
2. Next, use a natural conversation prompt to tell your agent exactly what audio you need—for example, 'Dub this video into Italian' or 'Generate speech for X text using voice Y.'
3. Finally, the system triggers the necessary pipeline, and you receive confirmation of the job status, tracking ID, or the generated audio file.

## Frequently Asked Questions

**How do I check my remaining character count using ElevenLabs MCP?**
You use the `get_subscription` tool to pull detailed usage information. This instantly shows your current billing cycle status and how many characters you have left for generation.

**Can I dub a video into multiple languages at once with ElevenLabs MCP?**
Yes, the system handles multi-language queues via the dubbing tools. You simply prompt your agent to translate and synthesize the audio across all necessary target languages.

**What is the difference between `text_to_speech` and `get_voice` in ElevenLabs MCP?**
`text_to_speech` actually generates the audio from a block of text. In contrast, `get_voice` only pulls metadata and details about a specific voice profile so you know exactly what voices are available.

**Where can I find my past ElevenLabs jobs?**
You use the `list_history` tool to retrieve an overview of all your previous audio generation activities. From there, you can call `get_history_item` for deep details on a single job.

**Does ElevenLabs MCP handle complex pronunciations?**
Yes, it does. If specific words are tricky, you use the `list_pronunciation_dictionaries` tool to guide your agent and ensure those words are pronounced correctly in the final audio.