All Voice Lab MCP
@allvoicelab
Official AllVoiceLab Model Context Protocol (MCP) server, supporting interaction with powerful text-to-speech and video translation APIs. Enables MCP clients like Claude Desktop, Cursor, Windsurf, OpenAI Agents to generate speech, translate videos, and perform intelligent voice c
概要
What is All Voice Lab MCP?
All Voice Lab MCP is the official Model Context Protocol (MCP) server for AllVoiceLab, integrating text-to-speech, video translation, and other voice APIs. It enables MCP clients like Claude Desktop, Cursor, Windsurf, and OpenAI Agents to generate speech, translate videos, and perform voice cloning, serving scenarios such as short drama localization and AI-generated audiobooks.
How to use All Voice Lab MCP?
Obtain an API key from AllVoiceLab, install uv (Python package manager), then configure the MCP client (e.g., Claude Desktop, Cursor) with the JSON config including ALLVOICELAB_API_KEY and ALLVOICELAB_API_DOMAIN environment variables. Optionally set ALLVOICELAB_BASE_PATH for output file storage. No additional setup is needed beyond that.
Key features of All Voice Lab MCP
- Multi-engine technology for speech, video, and voice cloning
- AI Voice Generator (TTS) in 30+ languages with high realism
- Voice Changer for real-time voice conversion
- Multilingual dubbing with emotional tone preservation
- Speech-to-Text (STT) with over 98% accuracy
- 3‑second ultra‑fast voice cloning
- Subtitle removal and extraction via OCR
Use cases of All Voice Lab MCP
- Convert text to speech in multiple languages
- Translate and dub video speech into different languages
- Clone a voice from a short audio sample
- Remove hardcoded subtitles from video files
- Extract subtitles from video using OCR
- Translate text files between languages
FAQ from All Voice Lab MCP
What dependencies or runtime are required?
The server requires uv (Python package manager) and an active API key from AllVoiceLab. No other runtime dependencies are listed.
Where are output files stored?
Output files are stored in the directory specified by the ALLVOICELAB_BASE_PATH environment variable, which defaults to the user’s home directory if not set.
How is authentication handled?
Authentication is done via the ALLVOICELAB_API_KEY environment variable. API domains differ by region (global or mainland China), and the key must match the region.
What transports does the server use?
The server communicates over HTTP/HTTPS to the AllVoiceLab API. No other transport (e.g., stdin/stdout) is documented.
Are there any known limits?
The README does not mention specific rate limits or usage caps. AllVoiceLab credits are required to use the tools.
