MotionShine01 / Listen
Written out
Whisper, an open speech model, writes out what you say, with times.
Free tool
YouTube chapters, from the video itself.
Drop in your video, or just its sound, and get chapter timestamps ready to paste into the YouTube description. The speech is written out, the places where the topic changes become chapters, and each one gets a short title you can edit. YouTube's rules are checked for you: 0:00 first, at least three chapters, each 10 seconds or longer. It runs in this tab, so your video is never uploaded.
For the description
Video
Titles come from each chapter's own words; in Chrome with its built-in AI ready, the AI names them. Change any title or time before you copy.
Your video is processed in your browser. Nothing is uploaded.
How it works
Listen, split, name.
02 / Split
Where the topic changes
Chapters start where the words you use change most, at the start of a sentence.
03 / Paste
Into the description
Edit titles and times, then copy the list. YouTube turns it into chapters.
Questions
Good to know.
How do I add chapters on YouTube?
Paste the list into the video's description, each line a time and a title, the first at 0:00. YouTube's help page asks for at least three chapters of 10 seconds or more, listed in order.
Is my video uploaded?
No. The speech model runs in this tab. Only the sound is used, so you can drop the MP3 or M4A instead of a large video.
Does it work for videos without talking?
It needs speech, since chapters come from what is said. For a music video or a silent screen recording, add chapters by hand with the Add a chapter button.
Can it write the whole description?
Yes, with the YouTube description generator: paste these chapters into it with your links and hashtags.
Which languages work?
The speech can be in any of the languages listed. Titles from the chapter's own words work in all of them; Chrome's AI names chapters in English.