Skip to main content
📖 The AI Tool Bible
Horch preview image
Horch logo

Horch

Not yet source-checked

Privacy-first, on-device meeting assistant for macOS

Machine-drafted from the vendor's site · not yet source-checkedProfile updated Link checked Pricing captured How we rate

Paid· One-time purchase: €49 onceAudioWhisper (local) for transcription; optional Ollama / MLX local LLMs for summarization

In short

Horch is a privacy-first macOS meeting assistant that transcribes calls locally using Whisper. It stores notes as Markdown and supports MCP for AI integration.

Best for

Privacy-conscious macOS knowledge workers, consultants, lawyers, therapists, and founders who run many meetings and want a local, Markdown-native record they can pipe into Claude or Cursor via MCP.

Skip if

Windows or Linux users, distributed teams that need a shared cloud workspace, or anyone who wants a hands-off SaaS with built-in CRM/Slack/HubSpot integrations.

Horch is a privacy-focused meeting assistant for macOS that captures, transcribes, and organizes spoken conversations entirely on-device. Instead of joining calls as a bot the way Otter, Fireflies, or Read.ai do, Horch records at the operating-system level, then runs Whisper locally to produce transcripts without sending audio to the cloud. From those transcripts it extracts action items, generates topic summaries, and builds people pages that accrue discussion history and open follow-ups over time, so every recurring contact effectively gets a living dossier. Everything is written as plain Markdown into ~/Meetings, which means the resulting knowledge base is diff-able, greppable, and portable to any other tool that reads Markdown (Obsidian, Logseq, ripgrep, editor search). It also exposes those notes over the MCP protocol, so Claude, Cursor, and other MCP-aware assistants can query your meeting history directly and use it as long-lived context. A CLI is provided for scripting and batch operations. The intended user is a knowledge worker who runs many meetings, cares about confidentiality (legal, medical, executive, security work, or anyone under NDA), and doesn't want a SaaS vendor storing recordings or transcripts. Because processing is local, there's no per-minute transcription fee and no bot showing up in the participant list; because storage is Markdown on disk, the notes outlive the app itself. Optional local model backends (Ollama, MLX) let users choose their own summarization model without ever leaving the machine.

Editor's take

Horch is the meeting-notes tool I recommend to people who visibly flinch when a bot joins their call. The on-device Whisper pipeline plus plain-Markdown output plus MCP server is exactly the right shape for 2026: your transcripts stay yours, and your agents can still read them. The €49 one-time price is refreshing, but you're buying into a macOS-only, single-user product — that's the trade.

— The AI Tool Bible editorial team

Pros

  • ✅ Fully on-device by default — audio and transcripts never leave the Mac unless the user opts in
  • ✅ One-time €49 purchase instead of a recurring per-seat SaaS bill
  • ✅ Records at OS level so no bot appears in the meeting and any app (Zoom, Meet, Teams, in-person) works
  • ✅ Notes stored as plain Markdown in ~/Meetings — portable, greppable, Obsidian-friendly
  • ✅ Auto-generates action items, topic summaries, and per-person profiles from spoken content
  • ✅ MCP server exposes meeting history to Claude, Cursor, and other agent clients
  • ✅ Local Whisper transcription plus optional Ollama/MLX means you pick the summarizer

Cons

  • ⚠️ macOS only — no Windows, Linux, iOS, or web client
  • ⚠️ Local Whisper and summarization need a reasonably modern Apple Silicon Mac to feel fast
  • ⚠️ No cloud sync or team workspace, so sharing across a team requires bring-your-own storage
  • ⚠️ Small independent product without the integrations catalog of Fireflies, Otter, or Fathom
  • ⚠️ OS-level capture depends on macOS screen/audio permissions, which some corporate MDM setups block

Pricing (captured )

TierMonthlyAnnualKey features
Install—€49 once
  • includes a year of updates
  • perpetual license
  • 2 Macs per license
  • 30-day free trial
Renew—€25/year
  • extends the update window by another year
  • optional renewal
  • never required

Prices change; we show the grid as captured on Oct 23, 2026. Check current pricing on the vendor's site →

Facts

API available
Yes
Model used
Whisper (local) for transcription; optional Ollama / MLX local LLMs for summarization
Hacker News
1 story · top 1 points · last Jul 24, 2026 · checked Nov 13, 2026

Where this tool sits

Use cases

Confidential client meeting transcriptionAutomatic action-item extractionPer-contact relationship historyPre-meeting briefings from prior callsLocal Whisper transcription without cloud uploadFeeding meeting context into Claude or Cursor via MCPPersonal second-brain in MarkdownLegal, medical, or NDA-bound conversation notes

Frequently asked

How much does Horch cost?
Horch is a one-time purchase priced at €49. There are no recurring subscription fees or per-minute transcription charges because all processing happens locally on your device.
Does Horch work on Windows or Linux?
No, Horch is exclusively for macOS. The documentation explicitly advises Windows and Linux users to skip it, as it relies on operating-system-level recording features specific to that platform.
Can I integrate Horch with AI tools like Claude?
Yes, Horch exposes meeting notes over the MCP protocol. This allows MCP-aware assistants like Claude and Cursor to query your meeting history directly and use it as long-lived context.
Is my audio data sent to the cloud?
No, Horch processes everything on-device. It uses local Whisper for transcription and optional local LLMs for summarization, ensuring audio and transcripts never leave your machine.
What format are the meeting notes stored in?
Notes are written as plain Markdown into the ~/Meetings directory. This makes them diff-able, greppable, and portable to other tools like Obsidian, Logseq, or standard editor search.

Compare Horch with similar tools

All alternatives →

Explore related

Reviews