Skip to content

Conversation

@alexander-zuev
Copy link

Hey Steven :) I've stumbled upon this repo while searching for alternatives to my own tool and decided to list since I didn't find any.

Opened a PR to add Typist to the Speech-to-text section in DISCOVERIES.md.

Typist is a lightning-fast AI audio & video transcription service built on top of latest Whisper models hosted on Groq.

What makes it different:
Speed: 1-hour audio → transcript in <20 seconds (40x faster than typical whisper-v2, 216x faster than real-time)
Accuracy: ~10-20% fewer errors than whisper-v2
UX: Synced playback with follow-along highlighting. Export to DOCX, PDF, TXT, and SRT formats.
Free tier: I've built this to solve my own pain point as well as for anyone who needs reliable and fast transcription, for example students. Typist has a generous free-tier available for all, no credit card required.

@alexander-zuev
Copy link
Author

Hey :) Bumping this up

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant