Your agent cannot listen to audio. harken fixes that — locally. MCP server + CLI, one 13 MB binary, fully offline: no Python, no ffmpeg, no API key.
Your agent cannot listen to audio. harken fixes that — locally.
An MCP server that transcribes WhatsApp voice notes, meeting recordings — any audio — so your agent can read them. One 13 MB binary powered by whisper.cpp, fully offline: no Python, no ffmpeg, no API key, nothing leaves the machine. The same binary is also a batch CLI and a Claude Code Agent Skill.
Five Portuguese voice notes explaining one task — transcribed on CPU, read by the agent, and answered in five bullets. Nothing left the machine.
Install the binary (Linux/macOS; more options):
or, in a project .mcp.json (Claude Code) / claudedesktopconfig.json (Claude Desktop):
That is the whole setup. Two tools appear — transcribefile and transcribewhatsappexport — and any MCP client can use them: Claude Code, Claude Desktop, Cursor, Windsurf. Hand the agent an .opus, an .mp3, a whole WhatsApp chat-export zip; it transcribes locally and reads the text.
Model, language and device are fixed per server instance (harken mcp --model medium --lang auto) with the same defaults as the CLI (small, pt, cpu) — run two entries for two languages. A first call with an uncached model downloads it inside that call (~466 MB for small); pre-warm with any CLI run (harken --model small some.opus) if your client times out long tool calls.
A coworker explains one task in five voice notes of 1–2 minutes each. That is ten minutes you have to sit through in order — and at the end you still cannot search it, quote it, or paste the one sentence that mattered into a ticket.
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/montezuma-p--harken.html)
MCP server: turn narrated screen recordings into agent-ready data — local Whisper transcript, scene keyframes, OCR, wall-clock anchoring. Record your screen, talk — your AI agent files the bugs.
Smitner-Studio/facetRender agent-written Markdown as a live local page, and send the human's click back to the agent as typed data. Human-in-the-loop approval gates for coding agents.
omaekumiko2-create/kruLocal-first MCP password and credential manager for AI agents. Use passwords, API keys, SSH identities, and TOTP without exposing hidden plaintext to the model.
CogniSwitch/KL4ATurn SOP, policy and regulatory documents into human-verified Open Knowledge Format (OKF) bundles — every claim carries its source span. Desktop app + CLI + MCP server.
menot-you/n-memoryMemory your agent can trust — every answer carries its source; when it doesn't know, it says so. Hermetic, local, MCP.
Kaseban/batonConvert AI coding sessions between Claude Code, Codex, OpenCode, Zed, Aider, Gemini CLI, Cursor, Cline & more — lossless, round-trip tested. MCP server + CLI.
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.