Whisper Notes
About
Search, read, and create speech-to-text transcripts on-device with the Whisper Notes Mac app — 100% offline, no open ports.
Details
- Author
- Unknown
- Categories
- Productivity, Other
Jump to
The examples below use the short aliaswn. Ifwnis already taken on your Mac (e.g. by WordNet), the full commandwhispernotesworks identically.
$ wn status WhisperNotes 1.5.5 (340) · SenseVoice Small · ready · 3081 notes $ wn list --limit 3 9f3c21a8 2026-08-01 09:14 0:42 meeting Weekly sync — pricing review b2d84e07 2026-07-31 18:03 12:26 recorded Idea dump on the walk home 5a1f9c33 2026-07-30 10:52 47:10 imported interview-with-anna.m4a $ wn transcribe ~/Desktop/standup.m4a Morning standup. Sarah shipped the pricing page, Marco is blocked on the… ✓ done in 6.5s (46x realtime) — saved to WhisperNotes history $ wn export --format md --audio --output-dir ~/Transcripts ✓ exported 312/312 transcript(s), 312 audio file(s) → /Users/you/Transcripts
Transcripts print to stdout, progress and errors go to stderr — safe to pipe or redirect anything. Add--jsonfor machine-readable output. Everything else is in thecommand reference.
The MCP server is built into the same binary — nothing else to install.
claude mcp add whispernotes -- whispernotes mcp
Claude Desktop— add this to~/Library/Application Support/Claude/claude_desktop_config.json, then restart Claude Desktop:
{ "mcpServers": { "whispernotes": { "command": "/usr/local/bin/whispernotes", "args": ["mcp"] } } }
- "Read my last five transcripts and tell me what I should follow up on."
- "Find the meeting where we discussed the invoice, and draft a reply email."
- "Transcribe ~/Desktop/podcast.mp3 and pull out every action item."
- Any local MCP client works the same way — commandwhispernotes, args["mcp"](Cursor, etc.).
- If the command isn't found, use the full path fromwhich whispernotes— GUI apps don't read your shell's PATH.
- The claude.ai website can't reach local MCP servers — use Claude Desktop instead.
# Summarize your latest recording with a local LLM wn show latest | ollama run llama3 "Summarize the key points:" # Transcribe an interview straight into the clipboard wn transcribe interview.mp3 | pbcopy # Who said what — speaker-labeled transcript of your last meeting wn show latest --speakers # Find that one conversation wn search "quarterly review" # Review only your meeting recordings wn list --source meeting --limit 10 # Switch the transcription model, then see which languages it takes wn models select sensevoice wn language list
- wnis a convenience alias forwhispernotes— identical commands. Scripts and AI agents should callwhispernotes, which always exists; the alias is only created when the name is free.
- Self-discovery for agents:whispernotes helpprints the full usage; a misused command replies with its exact usage line on stderr.--jsonalways emits a single JSON object or array on stdout.
- showtakes the full id or just its first 4+ characters as shown bylist— orlatest, which is the default.
- --speakers(onshowandexport) uses the speaker detection you've already run in the app;exportquietly falls back to plain text for notes without it.
- exportwrites date-titled files (2026-08-01-1956 Standup.md), never overwrites, and defaults to./whispernotes-export; Markdown files carry date, duration, source, and id up top.
- --sourcefilters by origin:recorded,imported,meeting, orfn(Fn-key voice typing).
- transcribeuses the model and language currently selected in the app, and the result is also saved into your history.
- If Whisper Notes isn't running, the CLI launches it in the background and waits up to ~15 seconds.
Long recordings are paged: when a transcript exceedsmax_chars, the response ends with an explicit truncation marker telling the agent whichoffsetto continue from — hour-long meetings never overflow a context window.
- Transport is a Unix domain socket at~/Library/Application Support/WhisperNotes/api.sockwith0600permissions — no TCP port, no network interface, unreachable from any other machine.
- Off by default: nothing is served until you enable the toggle in Settings.
- MCP clients like Claude ask for your approval before each tool call.
- Transcription runs on-device with the same engines as the app; results are stored only in your local history.
- command not found: whispernotes— install the command-line tool fromSettings → Integrationsin the app, then open a new terminal window (bothwhispernotesandwnshould work).
- "the local API is disabled"— enableSettings → Integrations → Local CLI & MCPin Whisper Notes. It applies instantly, no restart needed.
- "The running WhisperNotes does not include Local API support"— your app predates the Local API. Update to 1.5.5 or later via the in-app updater or thelatest DMG.
- First transcription is slow to start— the model may still be loading; the server waits for it to become ready.whispernotes statusshowsloading model…until the engine is warm.
- Download Whisper Notes for Mac (DMG)
- Changelog
- Privacy policy
- Raw markdown of this page for agents:whispernotes.app/cli-mcp.md
- Questions or ideas:support@whispernotes.app
Interact with Apple Notes using natural language on macOS.
Let your AI assistant directly manage calendar, email, notes, and control any Mac app.
Local macOS notebook that is also an MCP server. Any AI assistant — Claude, Cursor, ChatGPT, Cline, Zed — reads and writes your notes. 22 tools. Free, local, private.
Have your agent start dictation (OSX only)
Voice-first note-taking app with MCP integration for Claude Code, Claude Desktop, Cursor, etc.
Access and manage Apple Notes on macOS via AppleScript.
Python tools for MCP that integrate with native Apple applications like Messages, Notes, Mail, and more on macOS.
Voice-first planning app. Dictate voice notes on iOS/Apple Watch, AI creates structured tasks and events. 21 MCP tools (read + write). Connect from Claude Code, Cursor, Windsurf. Free trial with promo code MCPBETA26.
Reads text aloud locally on Windows, macOS, and Linux using the operating system's built-in speech engine. No API key, no account, no special hardware required, and no cloud service — text never leaves the machine.
The knowledge OS every AI can read from — persistent memory MCP server over your saved YouTube, articles, PDFs, and notes.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.




