Local Whisper MCP
A community-built MCP server that enables private, local audio and video transcription using the Whisper model. It supports various audio formats (WAV, MP3, M4A) and video files (MP4, WebM) by extracting audio tracks. The server runs on GPU (Vulkan/Metal) or CPU, downloads models from Hugging Face with hash verification, and outputs plain text, SRT subtitles, or JSON segments with timestamps. It is designed for privacy as processing occurs entirely on the user's machine.
Package and access
Local package with source-attributed installation metadata. Koskamo does not execute packages during review.
What you can do with it
- Transcribe voice notes and meetings into text locally
- Generate SRT subtitles from video files
- Convert audio recordings to JSON with timestamps
Source and maintenance
- Maintenance checked
Packages and installation
Source-provided package data. Koskamo has not executed or live-probed this package.
https://github.com/OrihuelaConde/local-whisper-mcp/releases/download/v1.0.0/local-whisper-mcp-1.0.0-osx-arm64.mcpb
{
"transport": "stdio",
"fileSha256": "c27f1cd42d75bb5197db2ba5dbddcf79ebe3b44892502fc304cc9636a1d00d55",
"identifier": "https://github.com/OrihuelaConde/local-whisper-mcp/releases/download/v1.0.0/local-whisper-mcp-1.0.0-osx-arm64.mcpb",
"registryType": "mcpb"
}Tools
Reported by the attributed source; not independently observed by Koskamo.
Let your agent find its tools
Find servers like Local Whisper MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.