Skip to content
SPECIFICTION
Get listed

Diktafon

github.com

Free plan WindowsmacOSLinuxiOSAndroid
Visit github.com
Spec score 8.3 #11 of 34 in Voice Note Apps

What it is

Diktafon is a voice memo app that transcribes and summarizes recordings on the device, then groups them into topic-based cassettes. It uses Whisper for transcription and Qwen for summaries; the models download on first run and can be changed in Settings. Each memo’s spoken language is detected, so recordings in different languages can sit in one cassette. Tap a transcript word to jump playback to that point in the recording. Cassettes can be exported as archives with audio and readable text, and imported content is added without overwriting existing items. The privacy policy says recordings, transcripts, summaries, labels, and settings remain in private app storage, and that the app collects and shares no data. Its stated network activity is limited to model downloads over HTTPS from Hugging Face and its CDN at the user’s request. The project is designed by Jaromír Janisch and is free and open source, with support for Android, iOS, Linux, and macOS.

Spec sheet

Purpose
Diktafon is a voice memo app that transcribes and summarizes recordings on the device and organizes them into topic-based cassettes.Read 2 Oct 2026 · github.com
Support
The privacy policy lists [email protected] and opening a GitHub issue as contact options.Read 2 Oct 2026 · github.com
Headquarters
Všenory, CzechiaRead 23 Sep 2026 · github.com
Maker
The project says it was designed by Jaromír Janisch.Read 2 Oct 2026 · github.com
Accounts and analytics
The app has no user accounts, analytics, crash reporting, advertising, or third-party service SDKs, according to its privacy policy.Read 2 Oct 2026 · github.com
Android requirements
Android 7.0 (API 24) or newer is required, and 4 GB RAM is recommended for the default models.Read 2 Oct 2026 · github.com
Download verification
Each release ships a SHA256SUMS file, and the repository says release artifacts include GitHub build-provenance attestations.Read 2 Oct 2026 · github.com
Export and import
Cassettes can be exported as archives containing audio and readable text, and imports add content without overwriting existing items.Read 2 Oct 2026 · github.com
iOS requirements
The iOS app requires iOS 13.0 or newer, and the project recommends a recent device for the default models.Read 2 Oct 2026 · github.com
Languages
The spoken language is detected for each memo, so a cassette can contain recordings in multiple languages.Read 2 Oct 2026 · github.com
Linux requirements
The Linux instructions list libmpv, parecord, and ffmpeg as runtime dependencies, and say the build uses Ubuntu 24.04 with glibc 2.39.Read 2 Oct 2026 · github.com
Network use
The policy says the app’s only network activity is downloading machine-learning models over HTTPS from Hugging Face and its CDN at the user’s request.Read 2 Oct 2026 · github.com
On-device privacy
The privacy policy says recordings, transcripts, summaries, labels, and settings stay in the app’s private storage, and the app collects and shares no data.Read 2 Oct 2026 · github.com
Transcript playback
Tapping a word in a transcript jumps playback to that point in the recording.Read 2 Oct 2026 · github.com
Transcription and summaries
The app uses Whisper for transcription and Qwen for summaries, with models downloaded once on first run and switchable in Settings.Read 2 Oct 2026 · github.com

Plans and prices

Free and open-source Free No cost · no ads · MIT-licensed Read 2 Oct 2026 · github.com

Every Diktafon plan and price →

Strong points and limits

Strong points

  • Transcribes and summarizes recordings on the device
  • Detects spoken language for each memo
  • Transcript words jump to matching playback points
  • Exports cassettes with audio and readable text
  • No accounts, analytics, ads, or data sharing stated

Limits

  • Default Android models recommend 4 GB RAM
  • iOS requires version 13.0 or newer
  • Linux instructions list runtime dependencies

Who it suits

Diktafon suits people who want on-device voice memo transcription and summaries, with language-aware cassettes and exportable recordings. Android users need version 7.0 or newer; the default models recommend 4 GB of RAM.

Verdict

Diktafon combines on-device transcription, summaries, and cassette-based organization with audio and text export. It is free and open source, though model requirements and Linux dependencies are worth checking against your setup.

Where Specifiction places it

Alternatives to DiktafonAll alternatives →