At a glance
| Server URL | https://mcp.vocallab.ai/mcp |
|---|---|
| Transport | Streamable HTTP (remote, nothing to install) |
| Auth | Authorization: Bearer vl_live_…, or ?key= in the URL for clients without custom headers |
| Plans | Every plan, Free included; AppSumo lifetime licences from Tier 3 |
| Price | 1 point per 15 characters; about $0.12 per minute of audio |
| Languages | 200+ |
| Tools | 12, listed below |
Get an API key
Sign up free, then create a key on the API keys page. Keys start with vl_live_ and can be revoked there at any time.
Claude Code
claude mcp add --transport http vocallab https://mcp.vocallab.ai/mcp \
--header "Authorization: Bearer vl_live_YOUR_KEY"Claude Desktop and claude.ai
Open Settings → Connectors → Add custom connector, name it VocalLab, and paste the URL with your key on the end: https://mcp.vocallab.ai/mcp?key=vl_live_YOUR_KEY. The connector UI can't send headers, so the key rides in the URL. Treat that URL like a password.
Cursor, VS Code, Windsurf and other clients
Add the server to the client's MCP config (~/.cursor/mcp.json for Cursor; VS Code uses a servers key in .vscode/mcp.json instead of mcpServers):
{
"mcpServers": {
"vocallab": {
"url": "https://mcp.vocallab.ai/mcp",
"headers": { "Authorization": "Bearer vl_live_YOUR_KEY" }
}
}
}ChatGPT
Where your ChatGPT plan allows custom MCP connectors (developer mode), add a connector with the URL https://mcp.vocallab.ai/mcp?key=vl_live_YOUR_KEY.
Tools
| Tool | What it does |
|---|---|
generate_speech | Text to speech with any voice and model, up to 2,000 characters per call. Returns the audio inline, plus download and caption links. |
list_voices | Search the 260+ catalog voices and your own clones and designed voices. |
list_models | 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 by word. |
clone_voice | Clone a voice from a 15–30 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 the designed preview you like as a reusable voice. |
delete_voice | Delete one of your clones or designed voices. |
delete_speech | Delete a generation and its audio file. |
get_balance | Check that the key works and read your points balance. |
Try it
Once it's connected, ask the assistant in plain words, for example:
- “Read this paragraph in a calm British male voice and give me the MP3.”
- “Find a Spanish narrator voice and voice this script, then give me SRT captions.”
- “Design a voice for a grumpy old wizard and save it.”