All activity
Lamantin.io is a calm “upload → results” workspace for turning audio and video into clean text. It supports accurate transcription with optional speaker diarization, extracts text from PDFs (including scanned documents) and images via OCR, and generates instant summaries and text refactoring to make content easier to read and share.
LamantinAudio/video transcription, diarization, OCR, summaries
Andrei Khrystsiukleft a comment
Excited to launch Lamantin.io 🎧📝 Upload audio/video (or PDFs/images), get clean transcripts with optional speaker diarization, plus OCR and instant summaries/refactoring — all with transparent credit pricing and a privacy-first flow (processed then deleted). Would love your feedback: what file type or workflow should we optimize next?
LamantinAudio/video transcription, diarization, OCR, summaries