Upload the recording.
See the whole argument.

Upload the audio — Atlas Red transcribes it for you and builds the map from what it heard. mp3, m4a, wav and webm all work. If you already have a transcript or caption file, import that instead: it's cheaper and handles far longer recordings.

20 MB per file, with an outer ceiling of three hours — and the file size binds first. That's roughly half an hour of typical podcast audio, closer to an hour for low-bitrate speech. Interviews, talks, lectures, voice notes and recorded calls are usually comfortably inside; a full-length chat show often won't fit whole. Two honest ways round it: import the segment you actually care about, or — if the show publishes a transcript — import that instead.

The show's own website or RSS feed — nearly every podcast serves a direct MP3; the most reliable route, and often the only one for a big-name show. Overcast, Pocket Casts, Castro and most other apps have a download button that leaves a real file. Apple Podcasts and Spotify keep episodes inside the app, so take the file from the show's website. Your own recordings — voice memos, an interview, Zoom audio, a talk captured on your phone — are already files, and they're the case no link-based tool can reach at all.

No — Atlas Red doesn't fetch podcast URLs or subscribe to feeds. You download the episode and upload it. That's a real limit, stated plainly, and it buys the thing that matters more: a tool that takes a feed URL can only reach what was published, and most recordings worth mapping were not — the customer interview, the internal all-hands, the lecture you recorded with permission. Uploading a file works the same on all of them. YouTube is the one exception: a video link imports directly, since YouTube publishes captions that can be fetched instead of transcribed.

It reads for meaning rather than handing the transcript back. A summary is a shorter sequence — three sentences that could describe a hundred other episodes — and what went missing was never length, it was shape. A map restores the shape: everything on one surface, in relation to everything else, main threads side by side, detail folded under the point it supports, the digression visibly a digression. Overview gives a roughly 15-topic take, balanced around 40, detailed around 100 — and a sentence of focus narrows it to the one segment you're here for. Then edit it: collapse what you knew, merge two points, cut the half that wasn't interesting.

Yes — interviews and panels are the normal case. Name up to 20 fields before importing — Speaker, Claim, Evidence — and it fills them in where the recording makes it clear. A field is a request, not a guarantee: the AI is instructed never to invent a value it can't support, so a point the conversation didn't cover comes back with that field simply empty. An empty field is information; a confidently wrong one would be a trap.

More than a document — transcription is billed by the minute on top of building the map. An hour of audio typically lands in the tens of cents rather than dollars, and the app quotes the job before it runs, refusing to start one your balance can't cover rather than stopping halfway. Every new account starts with $1 of trial credit, valid 30 days, no credit card; then prepaid packs with no subscription and no expiry. Failed jobs are never charged.

Yes. With Atlas Red Pro you can connect your own AI account for transcription, for map building, or for both — no markup. Bring a key for only one step and you're billed credits for the other half; the quote shows which.