Transcribe Video to Text

Hi Fazier! I built this because copying a transcript out of YouTube by hand is painful, and most tools stop at one plain block of text. This one gives you a readable script split by speaker with timestamps, and exports straight to Word or SRT. YouTube captions are free and unlimited. For videos without captions it runs AI speech recognition, with a free monthly allowance. Would love to hear which sites you want it to support next.

Splitting the transcript by speaker with timestamps is what makes it quotable; one plain block is where most tools stop. For videos without captions, is there a length cap on the AI transcription? A 60-minute Loom or a recorded webinar is a common case. On sites to add next: course platforms like Udemy and Teachable would help students taking notes.

SRT export is the part I'd use most: pulling captions from my own videos to re-cut them as Shorts. Two questions from that angle: how are the SRT lines split, by sentence or by a max length? Long lines are hard to read on a vertical video, so an option for 2-3 words per cue would be great. And for TikTok links, does it use the creator's captions or always run the AI transcription?

Having the transcript in the side panel next to the video is handy for lectures. When a video has no captions, does the AI transcription run locally or in the cloud? And how does it handle speakers who talk over each other, does the speaker labelling hold up?