Launching today
Cutio
Skip YouTube sponsors with AI, even on TV
30 followers
Skip YouTube sponsors with AI, even on TV
30 followers
Cutio uses AI to detect sponsor reads and self-promotion in YouTube videos, then skips them automatically in your browser or on a paired TV. It works across creators, topics, and languages, and saves results to a shared cache so analyzed videos load instantly for everyone.
Hey Product Hunt!
I'm Dmitrii, the maker of Cutio
I built Cutio because I wanted YouTube to feel uninterrupted without manually jumping over sponsor reads and self-promotion
Cutio analyzes each YouTube video's transcript with AI, detects sponsor reads and self-promotion, and skips those parts automatically while you watch — in the browser or on a paired TV
Unlike community-based tools, Cutio can work on fresh, niche, and non-English videos before anyone has manually submitted segments
The goal is simple: open a YouTube video and let Cutio handle the parts you would normally scrub through by hand
What makes it different:
• works across languages, creators, and topics
• analyzes videos directly from their transcripts
• skips automatically in the browser
• can also skip detected segments on paired TVs
• pairs with YouTube on TV using a simple code, with no server setup
• shows detected segments progressively while analysis is running
• saves results to a shared cache, so analyzed videos load faster for everyone
• gives you simple filters for segment types, video categories, and maximum video length
• tracks time saved, skipped segments, and analyzed videos
• supports your own OpenRouter key if you want more control
Cutio is available for Chrome today, with support for more browsers coming soon
I’d love feedback on detection quality, TV pairing, edge cases, whether the interface feels simple and minimal, and what you’d like to see added next
@brolnickij I think the interesting question here isn’t whether people want to skip sponsor segments. Everyone does.
What I’m trying to understand is whether this remains accurate as creators adapt. More and more YouTubers are blending sponsors directly into the content instead of treating them as a separate block. Some channels even make the sponsor part entertaining enough that viewers don’t necessarily want it skipped.
Does that create a moving target for Cutio?
The other thing I’m wondering about is whether transcript analysis is enough on its own. A lot of YouTube content relies on context, tone, visuals, or transitions that don’t always show up clearly in transcripts. Have you found cases where the transcript suggests something is a sponsor segment but the actual video context says otherwise?
Also, what’s the long-term moat here? If transcript access and models continue to improve, it feels like detecting sponsor reads becomes increasingly commoditized. Is the real value in the detection itself, the TV experience, the shared cache, or something else entirely?
The problem is obvious and the solution is easy to understand, but I’m curious which part of the business you think becomes harder over the next few years rather than easier.
@moh_codokiai
Great questions!
I agree this is a moving target. Creators are getting better at blending sponsorships into the actual content, and sometimes those integrations are genuinely entertaining. I don't think Cutio should blindly skip every monetized mention.
The goal is viewer control, not aggressive removal.
Cutio is intentionally more conservative than aggressive right now. I'd rather miss some borderline cases than skip content someone actually wanted to watch. In my current benchmark, the best model reaches 86.0% F1, with 88.9% precision and 83.3% recall (https://cutio.dev/benchmark)
On transcripts: Cutio isn't only looking at raw subtitles. It also uses video context like the author, title, category, keywords, description, duration, and other metadata. But the transcript is still the main evidence. Metadata can suggest candidates, but the spoken content still needs to support the decision.
I'm also working on channel-level controls / whitelists. If you like how a specific creator does sponsorships, you should be able to keep watching those segments on that channel. The shared cache stores detected segments, but user settings decide what actually gets skipped during playback.
Long term, I don't think the moat is just "a model can detect sponsor reads". That will get cheaper and more common. The harder parts are trust, UX, TV pairing, shared cache, feedback loops, and giving users control without making the product feel complicated.
@brolnickij Creators have become increasingly dependent on sponsorship revenue, and many are actively designing integrations that feel less like ads and more like part of the video itself.
That seems like it creates an interesting challenge. The better creators get at making sponsorships feel natural, the harder they become to detect.
Has the detection problem become more difficult over time as creator behavior evolves, or has the improvement in AI models been keeping pace with that change?
@josh_bennett1
Yes, I think both things are happening at the same time.
Creator behavior is making the problem harder. Simple "this video is sponsored by…" segments are relatively easy to detect, but native integrations, product reviews, jokes, and sponsorships that are part of the story are much more ambiguous.
At the same time, AI models are getting much better at understanding context. Cutio doesn't only look for keywords like "sponsor" or "promo code". It looks at the transcript together with video context such as the title, author, category, description, keywords, and duration. That helps it understand whether something is actually off-topic promotion or part of the video.
I also publish benchmark results here if you want to see how different models perform on this task: https://cutio.dev/benchmark
But I don't think this will ever be a fully solved problem. The harder cases are subjective. Sometimes even humans would disagree on whether a segment should be skipped.
That's why I see Cutio less as "AI decides what is an ad" and more as a viewer-control tool. The model gives a good default, but the long-term product needs controls, whitelists, feedback, and personal preferences so users can decide how aggressive they want it to be.