TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Now I can just print that video

276 pointsby pforretover 1 year ago

31 comments

quartzover 1 year ago
Definitely would use this.<p>Instructional video instead of step-by-step text is a personal pet peeve. I know it&#x27;s a lot easier to just record a video to show something like &quot;how to replace the battery on a cordless vacuum&quot; or &quot;removing a sink basin nut&quot; but it&#x27;s often such a painful experience for consumption (watch a moment, pause, scrub back and watch again, pause, continue, pause, all with potentially gloved hands often in tight working spaces).
评论 #38521067 未加载
评论 #38520708 未加载
评论 #38521618 未加载
评论 #38538573 未加载
评论 #38522768 未加载
评论 #38533886 未加载
评论 #38519494 未加载
atticoraover 1 year ago
I saw a YouTube video by a guy who specializes in building D&amp;D characters. He spends twenty minutes going into detail on each one, and then makes the pitch for subscribing to his Patreon account with something like &quot;members get all the details in a convenient list so that you don&#x27;t have to keep going back to this video.&quot;<p>So he&#x27;s using the same bit of friction that this article is trying to solve, to fill his rice bowl. It&#x27;s a bit of a shame that fixing this problem for me will cause one for him.
评论 #38521697 未加载
评论 #38519053 未加载
评论 #38519066 未加载
评论 #38520661 未加载
binarymaxover 1 year ago
No need to spend hours trying to get the text extraction just right - pass the raw extraction into GPT and ask for it to give you the recipe.
评论 #38517930 未加载
评论 #38520454 未加载
cloudkingover 1 year ago
It&#x27;s a very cool technical feat, but not something I would personally pay for. I&#x27;ll just spend the 1-2 minutes to watch the video for free. Not trying to discourage you, just giving honest feedback. Launching the early landing page is a good idea to validate further.
avgcorrectionover 1 year ago
I could also need a service for trimming all of the fat from how-to articles.<p>&gt; We’ve all been there: we used the florb for too many glorbs and now it needs to be replaced. [...]<p>&gt; This is an experience that everyone at the staff of howto.biz.uk has had! [...]<p>&gt; But how do you replace a used-up florb? In this article we are going to show you how. [...]<p>&gt; [scan the next five paragraphs]
评论 #38524846 未加载
gsaover 1 year ago
This is pretty cool but I&#x27;d like to see a well-formatted recipe, not a transcript. I prefer the markdown format for recipes so I worked on something like this earlier this year [0]. It fetches Youtube subs (with no audio processing like the video itself like this project) and returns a markdown with ingredients and steps.<p>[0] <a href="https:&#x2F;&#x2F;github.com&#x2F;gaganpreet&#x2F;summarise-youtube-recipes">https:&#x2F;&#x2F;github.com&#x2F;gaganpreet&#x2F;summarise-youtube-recipes</a>
TrevorJover 1 year ago
As someone who&#x27;s learning was significantly accelerated by the &quot;written tutorial&quot; phase of the internet this would be a really great little tool. I find video tutorials to be far more cumbersome than text+ images.
RBerenguelover 1 year ago
I kind of wrote something for this a few years ago: <a href="https:&#x2F;&#x2F;github.com&#x2F;rberenguel&#x2F;glancer">https:&#x2F;&#x2F;github.com&#x2F;rberenguel&#x2F;glancer</a> [edited a fat-fingered copy-paste]<p>The use-case is technical videos (like from conferences) I’m interested, but not enough to invest 20-60 minutes.<p>Haven’t used it in a few months so the yt-dlp commands may need updating.
评论 #38522517 未加载
polygamous_batover 1 year ago
You can also use software to detect “cuts” in the video, which can be used to improve the frame-extraction over just getting six evenly spaced frames from the video.
评论 #38519560 未加载
评论 #38518198 未加载
评论 #38517658 未加载
hermannj314over 1 year ago
Do video formats support structured meta data to be embedded in them?<p>If I make a video of me cooking, can I embed the recipe in the video, etc. Not just visually, but i.e. at 10s, I digitally insert the data &quot;Add 1 cup red peppers&quot;. It isn&#x27;t necessary a caption of something said or shown, just extra data.<p>Could a video creator leave substantially more metadata in their videos? I always assumed the pop-up metadata was externally stored and timestamp synced. Is there a way to embed it?
评论 #38521462 未加载
评论 #38521843 未加载
jsharfover 1 year ago
Recommend passing the speech-to-text narration through a round of GPT4 API to correct for any transcription errors (use some prompt giving context that it&#x27;s speech to text)
xnzakgover 1 year ago
Wonder if Kagi&#x27;s universal summarizer would work on recipe videos. It seems to do a decent job on YouTube videos, but those usually have cc built in.
barrkelover 1 year ago
Great, a way to turn videos into something I can scan. Actually something I&#x27;d consider using.
jusquanover 1 year ago
This is great, thank you for sharing! I wonder what the reverse would look like. More and more nowadays, I find myself first looking on YouTube for tutorials and walkthroughs, even if they wind up being more verbose than their written counterparts.
pforretover 1 year ago
Using yt-dlp, ffmpeg and various AI services to print videos (e.g. cooking IG reels)
tgsovlerkhgselover 1 year ago
Based on the example shown on the page, the output doesn&#x27;t seem very good. If that&#x27;s one of the better examples the software produced, I don&#x27;t think this will be useful in practice.
评论 #38520581 未加载
lucubratoryover 1 year ago
An evolution of this process would make it feasible to do retrieval-augmented generation using information from video content. I&#x27;ve thought about trying to do this to improve the (already impressive) abilities LLM&#x27;s possess as a creative writing assistant&#x2F;rubber ducky; a lot of good writing advice is on YouTube in the form of video essays, tutorials, lectures, etc.
paledotover 1 year ago
The copyright notice on the output is a poor choice, since you almost certainly do not own the copyright to any of the content. You&#x27;ve gone to impressive lengths to ensure that the result is true to the source material, which means that there is no claim to this being a transformative work.<p>(Very cool and useful project, though.)
ForOldHackover 1 year ago
Ha! Print that video? Yes, but can you FIND THE PRINTER? ---- I humbly apologize, I thought this was some joke, or errant stupidity. Its not. This person has put some very serious thought into not only getting it to work, but to make it useful. Very useful. You have earned my Upvote, and recommendation. Thank you Mr Forret. Thank you.
zoomablemindover 1 year ago
If the main challenge was &#x27;not having the smartphone in the kitchen&#x27;, then one possible solution could have been getting another screen dedicated to the kitchen. A tablet, a laptop, a small TV+Google Cast or such combination.<p>It seems to be a proper media for &#x27;printing&#x27; a video.<p>Of course, choosing challenges and finding solutions is what drives fun.
评论 #38518196 未加载
评论 #38518128 未加载
roomeyover 1 year ago
These tik tok videos are pretty short right? Why not just get a note book and write down the instructions.<p>You could even do a little line drawing of the important bits.<p>You could keep this &quot;cook&quot; book in your kitchen, and maybe pass it to one of your kids (just an example) when they move out or something.
IgorPartolaover 1 year ago
I actually wonder if in the limit of video encoding we could just get a diffusion model that can in real time render realistic video based on a script. Then downloading a movie is just downloading a few megabytes of a prompt and you get a movie playing based off it locally.
评论 #38524313 未加载
评论 #38522783 未加载
adr1anover 1 year ago
Cool! I had the same project idea recently. You may be interested in this for the step of speech2text: <a href="https:&#x2F;&#x2F;github.com&#x2F;SYSTRAN&#x2F;faster-whisper">https:&#x2F;&#x2F;github.com&#x2F;SYSTRAN&#x2F;faster-whisper</a>
ada1981over 1 year ago
I think you could send all of that to GPT4 and ask it to read it and provide you with a step by step instruction : recipie and it would do so easily.<p>I didn’t see how that print out would be super useful, it’s not the complete step by step is it?
einpoklumover 1 year ago
Ok, so:<p>* It does not print the video frames as a 3D object.<p>* Despite what the graphic at the link suggests, it doesn&#x27;t 3D-print food<p>it extracts a recipe with images and text from a video, automatically.
incahootsover 1 year ago
Oh wow....this will incredibly useful for the influx of recent home improvement videos I&#x27;ve been watching lately.
1970-01-01over 1 year ago
Filtering a video for true content is the real app. Print is simply the format you&#x27;ve chosen to express it.
mannyvover 1 year ago
If there are YouTube-generated captions you can get yt-dlp to download them when you download the video.
benobover 1 year ago
For some reason I though the goal was to print (with a 3d printer) a 3d projection of the 4d content of the video. That would be cool...
评论 #38522849 未加载
评论 #38518741 未加载
Hugsunover 1 year ago
Great work! It&#x27;s potentially useful and also hilarious.
Gysover 1 year ago
Could have been a Show HN