Discover the toolingbehind modern intelligence
The operating system for AI infrastructure discovery. Search a live map of MCP servers, AI agents, LLM tools, automation systems, and developer infrastructure.
local-stt-mcp
A high-performance Model Context Protocol (MCP) server providing local speech-to-text transcription using whisper.cpp, optimized for Apple Silicon.
15stars
6forks
TypeScript
appleapple-siliconm1m2m3m4mcpmcp-serverspeech-to-textsttwhisperwhisper-cpp
Quality signals
StaleNo testsNo CIThin docsNo licenseNew
AI summary
Auto-generated overview of what this skill does and when to reach for it.
Local, private speech-to-text MCP server using whisper.cpp optimized for Apple Silicon with speaker diarization and multiple output formats.
Use this when
- You need private, offline transcription without cloud APIs
- You're on Apple Silicon and want 15x real-time transcription
- You need speaker diarization to identify who said what
- You have audio in MP3/M4A/FLAC and want automatic conversion to WAV
- You want output in SRT/VTT/JSON for subtitles or transcripts
Don't use when
- You need cloud-based transcription with higher accuracy models
- You're on Windows/Linux and don't have Apple Silicon
- You can't install ffmpeg or whisper.cpp locally
Capabilities
- 100% local processing with no internet required
- Apple Silicon optimized for 15x real-time transcription
- Automatic conversion of MP3/M4A/FLAC to WAV for whisper.cpp
- Speaker diarization to identify multiple speakers in audio
- Supports 6 output formats: txt/json/vtt/srt/csv
- Low memory usage under 2GB during operation
InstallMCPRun via npx (Node)
Universal installANY TOOL
$ npx skillcity@latest SmartLittleApps/local-stt-mcpAuto-detects the skill or MCP server in this repo and installs it for Claude Code, Codex, Cursor or Cline.
Requires Node.js 18+ (ships with npx).
Or install manually
npx -y local-stt-mcp
MCP Configuration
Add this to your claude_desktop_config.json
{
"mcpServers": {
"local-stt-mcp": {
"command": "npx",
"args": [
"-y",
"local-stt-mcp"
]
}
}
}Readme
Loading README…