Voicekeep

Whisper-quality transcription that runs entirely on your iPhone. No cloud, no upload, no paid minutes — just press record.

Voicekeep is a privacy-first voice recorder and transcriber. Audio is captured, transcribed, and summarized entirely on your iPhone — nothing is uploaded to any server.

POWERED BY WHISPER Voicekeep runs the Whisper speech-recognition model directly on Apple Neural Engine. State-of-the-art accuracy in 90+ languages, including English, Russian, German, French, Japanese, Korean, Chinese.

WORKS WITHOUT INTERNET Once a Whisper model is downloaded, Voicekeep works fully offline. Useful on planes, in courtrooms, in clinics, in interviews — anywhere reliable Wi-Fi isn't.

PROFESSIONAL FEATURES • Word-level timestamps with tap-to-seek playback • Search across every recording and transcript instantly • Edit transcript text to correct names and rare terms • Highlight key segments and filter by highlights • Manual speaker labels with color coding • Custom vocabulary biasing for legal, medical, and technical jargon • Export to PDF, Markdown, plain text, SRT, and VTT subtitles • Send transcript snippets to Reminders or Calendar with one tap • Translate any transcript using Apple's built-in Translation framework

APPLE INTELLIGENCE INSIDE (Pro+) On iPhone 15 Pro and later running iOS 26, Voicekeep uses Apple's on-device language model to: • Generate concise meeting summaries with action items • Suggest topical tags automatically • Answer questions about any recording

PRIVACY BY DESIGN • Audio is processed entirely on-device. • No analytics SDKs, no third-party trackers, no data collection. • Apple Privacy Label: "Data Not Collected". • Open-source Whisper models. You can audit what runs.

Your voice. Your iPhone. Nothing else.

Terms of Use (EULA): https://www.apple.com/legal/internet-services/itunes/dev/stdeula/