- Home
- Voice Note Apps
- Diktafon
Diktafon
Všenory, Czechia
What it is
Diktafon is a voice memo app that transcribes and summarizes recordings on the device, then sorts them into topic-based cassettes. It uses Whisper for transcription and Qwen for summaries; the models are downloaded at first run and can be changed in Settings. The app detects the language of each memo, so one cassette can hold recordings in multiple languages. Selecting a word in a transcript jumps playback to that point in the audio. Cassettes can be exported as archives with audio and readable text, and importing adds material without replacing existing items. The privacy policy says recordings, transcripts, summaries, labels and settings stay in private app storage, with no data collected or shared. Its only stated network activity is downloading models over HTTPS from Hugging Face and its CDN at the user’s request. Diktafon has no accounts, analytics, crash reporting, advertising or third-party service SDKs. It is free and open source. Android requires version 7.0 or later, with 4 GB RAM recommended for default models; iOS requires version 13 or later.
For and against
For
- Transcribes and summarizes recordings on the device
- Transcript words jump playback to matching audio
- Cassettes support recordings in multiple languages
- Exports audio and readable text in archives
- No data collection or sharing, according to its policy
Against
- Android 7.0 or newer is required
- Default models recommend 4 GB RAM
- iOS 13.0 or newer is required
- Linux runtime dependencies include libmpv, parecord and ffmpeg
The verdict
Diktafon combines local transcription, summaries and cassette organization with archive export and transcript-linked playback. Its listed platform requirements and recommended memory are worth checking before choosing it.
Who it suits
Diktafon suits people who want on-device voice memos with transcripts, summaries and topic-based organization. It is available for Android, iOS, Linux and macOS.
Plans and prices
Free and open-source
No cost · no ads · MIT-licensed
Read 2 Oct 2026 · github.com
On the record
- Accounts and analytics
- The app has no user accounts, analytics, crash reporting, advertising, or third-party service SDKs, according to its privacy policy.github.com · read 2 Oct 2026
- Android requirements
- Android 7.0 (API 24) or newer is required, and 4 GB RAM is recommended for the default models.github.com · read 2 Oct 2026
- Download verification
- Each release ships a SHA256SUMS file, and the repository says release artifacts include GitHub build-provenance attestations.github.com · read 2 Oct 2026
- Export and import
- Cassettes can be exported as archives containing audio and readable text, and imports add content without overwriting existing items.github.com · read 2 Oct 2026
- iOS requirements
- The iOS app requires iOS 13.0 or newer, and the project recommends a recent device for the default models.github.com · read 2 Oct 2026
- Languages
- The spoken language is detected for each memo, so a cassette can contain recordings in multiple languages.github.com · read 2 Oct 2026
- 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.github.com · read 2 Oct 2026
- Maker
- The project says it was designed by Jaromír Janisch.github.com · read 2 Oct 2026
- 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.github.com · read 2 Oct 2026
- 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.github.com · read 2 Oct 2026
- Purpose
- Diktafon is a voice memo app that transcribes and summarizes recordings on the device and organizes them into topic-based cassettes.github.com · read 2 Oct 2026
- Support
- The privacy policy lists [email protected] and opening a GitHub issue as contact options.github.com · read 2 Oct 2026
- Transcription and summaries
- The app uses Whisper for transcription and Qwen for summaries, with models downloaded once on first run and switchable in Settings.github.com · read 2 Oct 2026
- Transcript playback
- Tapping a word in a transcript jumps playback to that point in the recording.github.com · read 2 Oct 2026
