Convert audio and video to accurate text in seconds. Powered by Whisper. 98+ languages, speaker recognition, translation, and one-click export.

Hey Product Hunt! 👋 I built Wavetype because most transcription tools either cap your minutes, lock the good features behind pricey tiers, or choke on long files. Wavetype keeps it simple: drop in an audio or video file (up to 10 hours / 5GB) and get accurate text back in seconds, powered by Whisper. What you get: 🎧 98+ languages, auto-detected 👥 Speaker recognition — who said what 🌍 One-click translation to 134+ languages 📄 Export to TXT, DOCX, PDF, SRT & VTT ⚡ Three modes — Cheetah, Dolphin & Whale — pick speed vs. accuracy ♾️ Unlimited plan with no minute caps Free to start (3 files/day, 30 min each). Unlimited is $10/mo billed yearly. I'd love your honest feedback — especially on accuracy and the editor. What would make this a daily tool for you?

Super fast and the speaker recognition actually works well, even with overlapping voices on a podcast clip. Way nicer than juggling other transcription tools I've tried.

being able to highlight a section of the transcript and have it jump straight to that timestamp in the audio would save me a ton of time when editing interviews.

love how the export flow is a single click instead of buried in menus, such a small thing but it makes the whole tool feel finished.

Super fast and the speaker recognition actually works well, even with overlapping voices on a podcast clip. Way nicer than juggling other transcription tools I've tried.

being able to highlight a section of the transcript and have it jump straight to that timestamp in the audio would save me a ton of time when editing interviews.

love how the export flow is a single click instead of buried in menus, such a small thing but it makes the whole tool feel finished.

Wavetype

Unlimited audio & video transcription, powered by AI

Unlimited audio & video transcription, powered by AI