speechmark sits in your menu bar, turns each meeting into a clean note — decisions, action items, the words that mattered — and keeps it on your Mac, where Claude Desktop and other MCP-aware AI can read and search your past meetings on demand.
One click to record. The mic, the meeting audio, both — speechmark handles the routing. No browser extension, no bot joining the call.
Speakers are separated automatically and labelled the first time you confirm a name. After that, every transcript reads like a script.
Decisions, action items, and a brief recap — in plain editorial prose. Pick the model that fits your privacy bar: Apple Intelligence, a local Ollama model, or your own OpenAI / Anthropic key. Click any line in the note to jump to the exact moment it was said.
Connect Speechmark to Claude Desktop and your transcript folder becomes a memory your own AI can reason over — privately, on your device. No competitor can hand you this, because their notes live in their cloud. Yours live on your Mac.
One click to connect. Settings → Assistant → Add to Claude Desktop. It installs as a Claude extension — no config files, no terminal, no API key.
Grounded in your meetings. Claude answers from your own notes — decisions, action items, attendees — and cites the meeting it came from.
Stays on your Mac. The connector reads your notes locally and makes no network calls of its own. You decide what any question surfaces.
Competitor data reflects their cloud-first defaults. Features may vary by plan.
I used to leave meetings with three pages of bullet points and no idea what we'd actually agreed. Now I leave with a paragraph that reads like a memo from someone who took it seriously.
Capture decisions and action items — not a wall of bullet points your team won't read.
Speechmark tracks who said what and when, so your sprint retros, PRD updates, and stakeholder readouts practically write themselves. Stay in the conversation instead of racing to keep notes.
Recordings and transcripts stay on your Mac. The only things that can ever leave are ones you switch on yourself — a cloud AI model (transcript text only) or anonymous usage stats. Both are off by default, and you control them.
Pick the AI model that fits your privacy bar — Apple Foundation Models (on-device, default), a local Ollama model (fully on-device, no API key), or your own OpenAI / Anthropic key — only the transcript text is sent, never the audio.
No. Recording and transcription happen entirely on your Mac, and the audio never leaves the device. If you pick a cloud AI model for the summary (OpenAI or Anthropic, with your own key), only the transcript text is sent — never the audio. You can also stay fully on-device with Apple Foundation Models or a local Ollama model.
Those are cloud-first: your audio is uploaded to their servers and you pay a recurring subscription. Speechmark keeps audio and transcription on your Mac, needs no account, doesn't send a bot into your call, and is a one-time purchase instead of a subscription.
No. Speechmark records the microphone and meeting audio directly from your Mac’s menu bar. Nothing joins the meeting, and other participants see no recording bot.
Speechmark is a one-time purchase of $79 per Mac, with no subscription. It’s currently a free public beta you can download and run today; buying now locks in a founding-customer price below the launch price.
macOS 14.2 (Sonoma) or later on an Apple silicon Mac.
Yes. Speechmark installs a local connector for Claude Desktop in one click — no API key, no config. Claude then answers from your own meeting notes and cites which meeting each answer came from, while the notes stay on your Mac.
Free during the public beta. No account, no credit card, no waitlist — download and run it right now.
It’s an early build, and your feedback shapes it. Found a bug or have a request? Send feedback →