Paste a YouTube link.
Get the talk as a map.

Copy the video's link — the address bar, the Share button, youtu.be, any of them; tracking parameters and playlist ids are ignored — and paste it into Atlas Red's import menu. Pick overview, balanced or detailed. The caption track is fetched, read for meaning, and built into an editable map, usually in well under a minute, since nothing has to be transcribed. The map keeps a link back to the video.

Yes. Atlas Red reads the transcript YouTube already holds rather than listening to the video, so an upload with no captions in any language can't be imported this way. That's checked first and costs a fraction of a cent, so you find out immediately rather than after paying for a job. In practice it is rarely the blocker: conference talks, lectures, interviews, tutorials and news almost always carry captions, auto-generated at minimum. Music videos and small unlisted uploads often don't.

No — and each is refused by name, not as a broken link. Shorts carry no transcript. A clip addresses a segment rather than a video, so open the full video. A playlist or channel is many videos with no single answer. A normal watch link that sits inside a playlist works fine.

Up to six hours, checked before anything is fetched. Past roughly three and a half hours of speech the transcript hits a 200,000-character cap and is truncated rather than refused — and both the import and the saved source say so. A partial map of a five-hour stream beats a refusal you can do nothing about.

The only structure a video hands you is a timeline: it tells you where you are and nothing about what's there. The thinking inside a good talk isn't linear — a main claim with two or three supporting lines, an objection raised and answered, a digression flagged as a digression — and it all reaches you at the same speed, spread along the same bar. A map lays it back out on one surface, in relation to everything else, so you take it in the way you read a diagram instead of playing it back. And it's a real map, not a picture of one: every topic editable, movable, exportable to 11 formats, and open to your AI assistant over MCP.

Yes. Name up to 20 fields before importing, in your own words — Claim, Evidence, Timestamp, whatever the talk calls for. A field is a request, not a guarantee: the AI fills one in only where the transcript genuinely supports a value and is instructed never to invent one, so a point the talk didn't cover comes back with that field simply empty. The other dial is depth — overview about 15 topics, balanced around 40, detailed around 100 — and a sentence of focus narrows the map to the part you're actually here for.

Whichever the video has. Your browser's language is a preference, not a demand: if the video doesn't carry it, Atlas Red falls back through the common languages and takes the first available track — preferring the uploader's own captions over auto-generated ones, because those are punctuated and spelled properly — then reports which language it used. Auto-translation is deliberately not requested: a machine translation of a machine transcription is a quality floor not worth paying a model to summarise.

Yes — the finished map keeps the video's title and a link back to the watch page, stored with it rather than in a note you'll lose. The transcript is kept alongside, so you can rebuild the map at a different depth without re-fetching anything. And because it's editable, the version you end up with is yours: collapse the branch you already knew, merge two points, cut the half that wasn't relevant.

The cheapest import there is, in two parts. Fetching the transcript costs under half a cent, because no model is involved. Building the map is the ordinary text price and the part that costs anything — around 10 to 30 cents for a full-length talk at balanced, a few cents for a short one. The $1 of trial credit every new account gets is good for roughly a dozen videos, valid 30 days, no card. After that, prepaid packs — no subscription, no expiry. Failed jobs are never charged.

For the map building, yes — Atlas Red Pro lets you connect your own AI account with no markup. The transcript fetch is the exception: it runs through Atlas Red's caption vendor, so it's billed as credits even for key holders. That's two calls per video, under half a cent — enough that a key-holding account needs a balance above zero, not enough to be worth thinking about after that.

No — only the caption text, never the audio or the video file. The link you paste is reduced to its eleven-character video id before anything leaves Atlas Red, so your URL is never forwarded anywhere.