nikhonit

Start your day with a personalized summary of new videos from your favorite YouTube channels — no more missing content from creators you actually want to follow.

Pain Point YouTube notifications are unreliable. You subscribe to channels, but their new videos never show up in your home feed. They're not in notifications. They just... disappear. This doesn't mean you don't want to see them — it means YouTube's algorithm buried them.

Plus: it's fun to start the day with curated content insights instead of doom-scrolling a recommendation feed.

What It Does Fetches the latest videos from a list of your favorite channels Summarizes or extracts key insights from each video's transcript Delivers a digest to you daily (or on demand)

Buy a dictionary, then understand the meaning of Slop. Not everything coming out of AI is a "slop"

Just clicks? Do Trivia for energies mate

A quick note for the developers/hackers here:

While building this, I realized most YouTube transcript APIs were either overpriced or lacked good integration for LLM workflows.

So I spun out the backend as a standalone API: transcriptapi.com

The cool part is I added native MCP (Model Context Protocol) support. If you use Claude Desktop or similar agents, you can drop this in as a tool to fetch full video context directly into your chat window without copy-pasting.

I built this because my YouTube 'Watch Later' playlist hit 500+ videos and became a source of anxiety rather than a queue. I wanted to know if a 2-hour podcast contained the specific citation I needed without watching the whole thing.

Under the hood: Recapio grabs the transcript (prioritizing manual captions over auto-generated ones) and uses an LLM to generate structured summaries with timestamped citations.

The Engineering Challenge: The biggest headache was 'hallucination drift'—where the AI summary claims a topic starts at 10:00, but it actually starts at 10:45. I solved this by implementing a chunking strategy that overlaps context windows, forcing the model to verify timestamps against the raw text segments before outputting the link.

It’s a work in progress. I'm curious if anyone has better strategies for handling the lack of punctuation in auto-generated YouTube captions

Note on speed: The audit takes about 15-20 seconds to run.

Since we are spinning up a headless browser to map the DOM before feeding it to the inference engine, it's not instantaneous like a regex check

I've noticed similar flakiness with MCP tools that rely on 'fire-and-forget' side effects depending on the client harness.