4 points ebukao | 2 comments | 10 Jul 25 17:14 UTC | HN request time: 0.463s
| source Last winter, my girlfriend was working on her university thesis and had to transcribe hours of interviews manually. I ended up helping her by running a local model of whisper and months later I decide to build a product out of it. It is a simple AI transcription tool that lets you upload audio or video and get clean, readable transcripts. It works well for thesis interviews, lectures, podcasts — anything spoken.
- Free plan for up to 30 minutes/month. - Supports audio and video files - Speaker Identification and labelling. - AI insight and summary. - Colorful tags to organize and filter your transcript - Upload custom vocabulary to help improve your transcription - Export to formats compatible with research tools like NVivo, Atlas.ti, MAXQDA, R / RStudio and SPSS - Built with privacy in mind (no training on your data) and many other features
The app is available on www.verbatimly.com
I’d love to get your thoughts — whether you're a student, researcher, or just someone who’s had to type out long interviews by hand. Let me know what works, what doesn't, and what would make it better.
Also, we are proudly made in Germany.
Happy to answer questions or help anyone get started!