VoiceMemo: Talk to Tasks

Recording is just the start. What matters is the follow-through.

Most voice apps stop when the transcript finishes — leaving promises, deadlines, and decisions buried in a wall of text. VoiceMemo is built around what happens after: impromptu capture anywhere from your Apple Watch and iPhone, intelligent meeting reminders, automated task extraction with two-way calendar & reminders sync, and deterministic structured context ready for your AI agents via native Model Context Protocol (MCP).

CAPTURE ANYWHERE: APPLE WATCH & IPHONE
• Apple Watch on your wrist — Complications, raise to speak, or Action Button. Record long meetings effortlessly right from your wrist.
• Meeting Radar & 1-Tap Record — Within 5 minutes of meeting start, your watch surfaces an upcoming meeting card; at start time, a haptic alert lets you 1-tap "Record Meeting" with title and attendees attached.
• Instant iPhone capture — Control recording right from Lock Screen widgets, Action Button, or Dynamic Island.

FOLLOW-THROUGH & TASK MANAGEMENT AT THE CORE
VoiceMemo recognizes who you are ("This is me") and intelligently extracts only what requires your follow-up:
• Your follow-up tasks only — Action items committed by you enter your global "My Tasks" hub without cluttering your to-dos.
• Spoken deadlines ("today at 6 PM", "next Monday") become real reminders with exact 24-hour times; fuzzy phrases ("ASAP") get one-tap suggestions.
• Each task has a ▶ timestamp button that replays the exact sentence where the promise was made.
• Bi-directional sync with Apple Reminders and Calendar — edits and completions stay in sync across devices.

NATIVE MCP & STRUCTURED CONTEXT FOR AI AGENTS
VoiceMemo is the first voice app with native Model Context Protocol (MCP) support:
• Connect directly to Antigravity, Codex, Claude, Cursor, GrokBot, Hermes, and OpenClaw — Agents query meeting notes, transcripts, action items, and personal context.
• 4 automatic scene templates (Meeting, Lecture, Journal, General) with a unified 6-part structure: Overview, Key Decisions, Action Items, Open Questions, Key Points, and Verbatim Quotes.
• High-signal context: Verified speaker identities, calibrated domain vocabulary, and structured tasks give AI agents grounded truth instead of noisy transcripts.

AUDIO SHARE SHEET IMPORT & SILKY 120FPS SCRUBBER
• One-tap Share Sheet Import — Share audio (.mp3, .m4a, .wav) directly from Apple Voice Memos, Files, WeChat voice messages, or external recorders for instant transcription.
• 120fps Silky Scrubber — Fluid audio scrubbing with zero decoder lag across recordings up to 3 hours long.

WHO SAID WHAT, ON THE RECORD
Multi-person recordings split by voice — up to 6 speakers labeled. Preview voice clips inline before naming them or marking "This is me", syncing across transcripts, summaries, and PDF exports.

IT LEARNS YOUR VOCABULARY
Spot a misheard name or term? Preview audio inline and batch-replace it across transcripts, summaries, and tasks in one pass. Confirmed terms save to your personal vocabulary (up to 100 terms).

ASK YOUR NOTES & GLOBAL SEARCH
Search globally across titles, summaries, transcripts, and tasks, or ask your entire note library in plain language with cited sources and one-tap audio jump.

BUILT NOT TO LOSE A WORD, PRIVATE BY DESIGN
Zero cloud dependency by default. Transcription runs locally on-device; audio stays safely on your phone and iCloud — never on our servers. Support for custom Gemini API keys gives you complete data ownership.

SIMPLE LIMITS
Every feature is on every plan. Free: unlimited recording and on-device transcription, plus 60 AI minutes/month. Pro raises the pool to 1,200 AI minutes/month with a 7-day free trial on yearly.

———
Subscriptions: VoiceMemo Pro is billed monthly or yearly through your Apple Account and renews automatically unless cancelled at least 24 hours before the end of the period. Manage anytime in Settings.
Terms: https://voicememo.work/terms
Privacy: https://voicememo.work/privacy