AudioPen vs Diktafon

AudioPen turns spoken thoughts into written text by transcribing speech and rewriting it in a style the user chooses. Users can set a low, medium, or high rewrite level, change output length, describe a style, or provide a sample to match. It can produce writing in a different language from the spoken input, and its site lists many supported languages. Voice typing works in text fields in apps such as Gmail, Slack, Notion, and Google Docs. Zapier and webhooks can send saved notes to other apps; Prime MCP provides ChatGPT or Claude read-only access to notes. Its iPhone, Android, Mac, and Windows apps offer on-device offline transcription, but AI rewriting needs an internet connection. The free plan permits recordings up to 3 minutes. Prime plans support recordings up to 15 minutes, with unlimited rewrites and note storage. The service is intended for individual thought: it does not join Zoom calls or label speakers. Voice-note audio is deleted from servers within 48 hours, and voice-typing audio is not saved.

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.