# VocalLab

> VocalLab is a freemium MCP server for design and media. Text to speech in 200+ languages, voice cloning, voice design and SRT captions. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Starting price:** $7.5 a month
- **Platforms:** API, Web
- **Website:** https://www.vocallab.ai/developers/mcp
- **MCP Registry name:** ai.vocallab/vocallab
- **Categories:** design and media
- **Listing updated:** 2026-11-16

## About

VocalLab's hosted server hands an assistant twelve voice tools. You can ask for a paragraph read in a calm British male voice and get the audio inline, with download and caption links, or have it find a Spanish narrator, voice a script and return SRT subtitles by phrase or word. Voices can be cloned from a 15 to 30 second sample or designed from a text description, previewed, and saved for reuse.

The catalogue has 260+ voices and four speech models: v-studio, v-flash, v-pro and v-lite. A single generation call is limited to 2,000 characters, and generated speech and cloned voices can be deleted through the same interface.

There is no extra fee for MCP. It uses the same points as the API, one point per 15 characters, which the site puts at about $0.12 per minute of audio. The free plan includes 60 points; paid plans start with Lite at about $7.50 a month and add commercial-use rights. Authentication is an API key beginning `vl_live_`, sent as a Bearer header or, for clients such as ChatGPT and claude.ai connectors that cannot send headers, in the URL, which should be treated as a password.

## Features

- **Speech generation:** Converts text to audio with a chosen voice and model.
- **Voice cloning:** Clones a voice from a 15 to 30 second sample.
- **Voice design:** Creates voices from a written description and saves the preview you like.
- **SRT captions:** Returns subtitles by phrase or word for a generation.
- **Voice and model search:** Lists catalogue voices, your clones and available models.
- **Balance check:** Confirms the key works and shows your points balance.

## Good for

- Narrate a script in a chosen voice from inside a chat
- Produce SRT captions for a voiced video
- Design a character voice and reuse it
- Clone your own voice for recurring voiceovers

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http vocallab https://mcp.vocallab.ai/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://mcp.vocallab.ai/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "vocallab": {
      "url": "https://mcp.vocallab.ai/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "vocallab": {
      "type": "http",
      "url": "https://mcp.vocallab.ai/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

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

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "vocallab": {
      "type": "http",
      "url": "https://mcp.vocallab.ai/mcp"
    }
  }
}
```

## Tools

- `generate_speech`: Text to speech with any voice and model, up to 2,000 characters per call
- `list_voices`: Search catalogue voices and your own clones and designs
- `list_models`: List the speech models v-studio, v-flash, v-pro and v-lite
- `get_speech`: Status and download links for a past generation
- `get_captions`: SRT subtitles for a generation, by phrase or word
- `clone_voice`: Clone a voice from a 15 to 30 second audio sample
- `list_voice_languages`: Languages and sample rules for cloning
- `design_voice`: Generate voice previews from a text description
- `save_designed_voice`: Keep a designed preview as a reusable voice
- `delete_voice`: Delete a clone or designed voice
- `delete_speech`: Delete a generation and its audio file
- `get_balance`: Check the key and read the points balance

## FAQ

### Which plans include MCP access?

Every plan, including Free, though AppSumo lifetime tiers 1 and 2 have limited access.

### How is usage charged?

One point per 15 characters, about $0.12 per minute of audio, the same as the API.

### Do I need to install anything?

No. It is hosted at mcp.vocallab.ai/mcp; clients that only run local servers can bridge with mcp-remote.

### Can I use the audio commercially?

Commercial use is included on paid plans; free plan audio is for personal use only.

### Is VocalLab free?

VocalLab has a free plan, with paid plans for more usage or features. Paid plans start at $7.5 a month.

### How do I add VocalLab to Claude Code?

Run this command in your terminal: claude mcp add --transport http vocallab https://mcp.vocallab.ai/mcp

### What are the best alternatives to VocalLab?

The closest alternatives to VocalLab are HyperFrames by HeyGen, ffmpeg-skill, AvatarSay — Fictional Character & Talking Video MCP, ChartAnt and VfxSmith.

## Alternatives

- [HyperFrames by HeyGen](https://ai-powered.com/mcp/hyperframes-by-heygen): HyperFrames by HeyGen is a freemium MCP server for design and media.
- [ffmpeg-skill](https://ai-powered.com/mcp/ffmpeg-skill): ffmpeg-skill is an open-source MCP server for design and media.
- [AvatarSay — Fictional Character & Talking Video MCP](https://ai-powered.com/mcp/avatarsay-fictional-character-and-talking-video-mcp): AvatarSay — Fictional Character & Talking Video MCP is a freemium MCP server for design and media.
- [ChartAnt](https://ai-powered.com/mcp/chartant): ChartAnt is a freemium MCP server for design and media.
- [VfxSmith](https://ai-powered.com/mcp/vfxsmith): VfxSmith is a freemium MCP server for design and media.
- [CalderFlow](https://ai-powered.com/mcp/calderflow): CalderFlow is a free MCP server for design and media.
- [Eikino](https://ai-powered.com/mcp/eikino): Eikino is a freemium MCP server for security.
- [Hourlore](https://ai-powered.com/mcp/hourlore): Hourlore is a freemium MCP server for design and media.

---
Source: https://ai-powered.com/mcp/vocallab
