sure, just brainstorming, but a good use case is xferring into google docs or other online collabs like google slides, confluence, etc.
I just did a cut and paste into google docs so I could split it apart and reference sections and my simple copy and paste including the headers "Transcription" every page, so if you could put those in a separate body/section of the doc that might help.
also, pdf is the king format, but perhaps otuputing to other doc formats would help people
one other thing I used to like in a transcription service from audio files I use is timestamps. there are many ways to do them and they could get cluttered. i usually turn them off for that other project, but since I'm doing this to critique a yt video, it would be handy to know at what times various things were said so I can go back and listen and also tell people "check out what he says at 1:35"
again, great job! i was surprised how fast and so far so accurate it is. I have not scrutinized it hard yet, but there are no obvious homophones (which plagues e.g. Zoom's AI summary/transcription).
Podcast apps have terrible search. Internet searches for good podcasts are flooded with click bait and promoted content. Instead, the approach here is to engage with podcasts by using natural language.
I just asked and this is what I got back: (1) if you're sure you want to complete your senior year, just wait till then to apply; (2) if you're not sure, apply now; (3) there's not currently any process for people who want to apply to batches farther out than the next one. I suppose (1) and (2) follow from (3) but there you go :)
Either way, good luck and please do apply when you're ready!
I developed this Chrome extension to set opening links in new tabs as the default behavior. Often, I found myself frustrated when intending to save a tab for later, only to have it replace my current one. While aware of the CMD+Click shortcut for opening links in new tabs, I prefer this as the default behavior, which is the reason I created this extension.
Foundational blocks to interact with Youtube API and LLMs to transcribe, summarize, and analyze Youtube videos. The API is designed to be minimal and customizable, allowing for easy integration with other services and APIs.
Foundational blocks to interact with Youtube API and LLMs to transcribe, summarize, and analyze Youtube videos. The API is designed to be extendable and customizable, allowing for easy integration with other services and APIs. Built using Flask, OpenAI's GPT-3.5-turbo, Youtube third-party libraries, and scraping techniques.
I've been developing this tool for generating AI-powered YB video transcriptions. It currently works very well for videos under 10 minutes, so I'm working on extending it for longer ones.
Built this Youtube Transcript AI tool which develops detailed transcripts with only a youtube link in over 50 languages, enhanced with AI-created titles, chapter divisions, concise summaries, and relevant tags.
I started this just a couple of days ago, so it's very buggy and bare bones.
Splitting paragraphs is a great idea, thank you!
Let me know anything else you would want; I'd love to implement it.