Turn lecture audio into
study notes you can actually review.

audien·to is an AI audio tool that turns a lecture recording into revisable study notes — numbered outline, key-term glossary, and self-check questions — in under a minute. Unlike a raw transcript you have to re-read, it gives you something you can actually study from. Free tier, 67 languages, no signup, audio auto-deleted in 72 hours.

Drop a recording of the class. We’ll pull out the outline, define the key terms, and write a short set of questions you can quiz yourself with — ready to paste into Notion, Obsidian, or Anki.

● Record
Drop audio here
or click to choose a file · up to 2h · auto-deleted in 72h
LANGUAGE
required · 67 supported
What you'll get
  • Outline
  • Key terms
  • Self-check questions
Speakers auto-tagged. Tweak any section after upload from the Options panel — no setup needed up front.
The guide

Why study notes from lectures matter

Re-watching a 50-minute lecture the night before an exam is a terrible use of time. Structured notes — outline, terms, questions — let you review the whole lecture in ten minutes.

The point isn’t to replace attending class. It’s to turn what was said into something you can actually study from, instead of a transcript that reads like a wall of text.

What good study notes contain

  • Outlinethe structure of the lecture, one line per section.
  • Key termsdefined, with the sentence where they came up.
  • Questionsshort self-check prompts, one per section.
  • Examplesworked examples preserved verbatim.

How audien·to structures yours

What lands in the doc

  • Outlinethe lecture’s actual structure, one line per section — mirrors the instructor, not a textbook.
  • Key termsdefinitions in the lecturer’s wording, plus the sentence where each first appeared.
  • Self-check questionsone open-ended prompt per section. Answers live in your notes; questions don’t.
  • Worked examplespreserved step-by-step with the instructor’s framing — these are what you’ll re-derive.
  • Reading listanything the instructor told you to read, with the section where they assigned it.

Writing study notes well

  • Mirror the lecture, not the textbookthe outline tracks how the class actually unfolded — that’s what shows up on the exam.
  • Cite the instructor’s wording“Cycle” means whatever Prof. Chen said it means, not Wikipedia’s version.
  • Open-ended questions only“Why does BFS find shortest paths?” beats “What is BFS?” — the second is a lookup.
  • Preserve examples verbatimworked examples are the most likely thing to reappear in modified form on the exam.
  • Note the emphasiswhat the instructor repeated or wrote on the board → almost certainly testable.

Knobs in the Options panel

  • Depthstudy-ready (one page) · full notes (multi-page) · cheat-sheet (key terms only).
  • Difficulty registerintro · intermediate · advanced — affects how definitions are framed.
  • Quiz density1 per section (default) · 1 every ~3 minutes of audio (denser review).
  • Examples handlingverbatim (default) · paraphrased (shorter, but you lose the instructor’s steps).
  • Lecture stylelecture (one speaker) · seminar (many speakers, attribute by name).
  • Domain vocabularySTEM · humanities · social science — biases term recognition and citation style.
Why this works

Why modern AI hears what older tools missed

When you upload audio, two AIs go to work. The first one listens. It learned from millions of hours of real speech — accented, overlapping, full of “ums” and brand names that didn’t exist five years ago — so it can hear “Klaviyo,” “Substack,” or “the GPT pipeline” without flinching. The words older tools used to silently mangle come back right.

It hears in context. Instead of guessing one sound at a time, it takes in the whole sentence and uses everything around a tricky word to figure out what was actually said. That’s how a brand-new product name still lands correctly: the words around it tell the AI what kind of sentence it’s in.

And it cleans as it goes. Disfluency — “uh, like, I think… yeah” — doesn’t drop the rest of the sentence on the floor. Punctuation and capitalization come built in, so what you read is prose, not a wall of lowercase. By the time it hands off, the transcript already looks like what a careful typist would have given you.

What happens once we have your words

A raw transcript is the floor, not the ceiling. The second AI reads the whole document the way a careful editor would. It groups related discussion into chapters even when nobody says “moving on.” It surfaces the quote you’d actually screenshot — not the longest sentence on the page. It separates a decision from a tangent, an action item from a passing wish.

That’s the jump older tools couldn’t make: they gave you words, we give you shape. A meeting becomes minutes with owners, dates, and resolved questions. A podcast becomes show notes whose chapters track the real narrative, not the nearest five-minute mark. A voice memo becomes a send-ready email in your voice — not a list of fragments to stitch back together.

Each tool on this page is one of those pairings — the same listening AI up front, the same writing AI behind it, shaped for one specific output. You don’t pick. You don’t tweak. A thirty-second upload comes back as the thing you actually wanted, ready to use.