Polotno transcribes audio and video into text with speaker labels, timestamps, and AI summaries. Upload a file or paste a YouTube/VK link — get punctuated, speaker-separated text exportable to TXT, DOCX, PDF, or SRT. Supports 99 languages.
Hi Product Hunt! I built Polotno to make transcription actually usable, not just "text dumped from audio."
What it does:
- Upload a file (up to 2GB) or paste a YouTube/VK/Rutube link — no manual audio extraction needed
- Speaker diarization + timestamps out of the box
- Optional AI summary with key points, so you don't have to read the full transcript
- Export to TXT, DOCX, PDF, or SRT
- 99 languages supported, including ones most tools skip (Kazakh, Uzbek, Armenian, Georgian)
Would love your feedback, especially on accuracy for non-English speech and what export formats you'd want to see next.