Skip to content
SPECIFICTION
Get listed

Cleft vs Diktafon

Cleft

cleftnotes.com

Diktafon

github.com

Side by side

FigureCleftDiktafon
Price from$3.33/moFree
Free planYesYes
Free trial——
Open source——
Windows—Yes
macOSYesYes
Linux—Yes
iOSYesYes
Android—Yes
Plans published31
Spec score · Voice Note Apps8.3 (#10)8.3 (#11)
HeadquartersDublin, IrelandVšenory, Czechia
SupportPlus includes priority support, and the About page says every email is read personally by co-founders Jonathan or Justin.The privacy policy lists [email protected] and opening a GitHub issue as contact options.

Plans

Cleft

  • BasicFree
  • Cleft Plus (monthly)$6.99 a month
  • Cleft Plus (annual)$39.99 a year

Cleft pricing →

Diktafon

  • Free and open-sourceFree

Diktafon pricing →

In their own words

Cleft

Cleft is an iOS and macOS app that turns spoken thoughts into notes with main points, actions, summaries, and transcripts. Its built-in output styles are Structured, Structured Prose, and Clean Transcript; Plus users can also save custom styles. Cleft says it works offline and supports 99 languages, including switching languages mid-sentence. Transcription runs locally using Whisper, and temporary audio is deleted afterward unless Keep Audio is enabled. Optional cloud formatting sends transcript text, not audio, to OpenAI, with Groq as a backup. Cleft lists support for iPhone, iPad, Mac, Apple Watch, and CarPlay. Its Basic plan includes recordings up to five minutes, on-device transcription, tags, search, and export. Plus raises the recording limit to 30 minutes and adds attachments, Notion and Zapier integrations, and Family Sharing for up to five. Plus costs $6.99 per month or $39.99 per year through the App Store, with automatic renewal unless canceled. Cleft says notes are encrypted at rest and in transit.

Visit cleftnotes.com

Diktafon

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.

Visit github.com