MP3, M4A (the format most phone voice-memo apps use), WAV, WebM, and OGG upload directly. Video files like MP4 and MOV work too — Scholarly transcribes the audio track and ignores the picture. Long recordings are fine, including multi-hour seminars, so you never have to split a file before uploading.
A transcript gives you the verbatim record — every sentence, in the order you said it. Notes are the condensed version: reorganized by topic, with the definitions and takeaways pulled out and the repetition removed. If what you mainly need is the word-for-word text with timestamps and speaker turns, use Lecture Transcription instead. Voice to Notes runs the same transcription underneath, then does the organizing for you — and keeps the transcript attached either way, so you never lose the source.
Better than you'd expect, with honest limits. Spoken thinking is naturally repetitive and out of order — that's exactly what the note-generation step fixes, because it groups ideas by topic rather than by the order they came out of your mouth. A rambling 40-minute voice memo usually becomes a tight one-page outline that reads back the structure of the idea, not the false starts.
What genuinely hurts quality is bad audio, not bad delivery: a microphone far from the speaker, heavy crosstalk, or loud background noise degrade the transcript the notes are built on. For anything high-stakes, check critical numbers and terms against the timestamped transcript — it takes seconds, and you're verifying against what was actually said.
The recording becomes a source in your Scholarly workspace, so everything builds on it without re-uploading: generate spaced-repetition flashcards or a practice quiz from the notes, ask the AI chat questions and get answers that cite the exact passage of the recording, or combine it with your PDFs and slides into one study set for the exam. Because the questions test how ideas connect — not whether you memorized a timestamp — the practice that follows builds real understanding.
New to the workflow? Our guide on how to turn lecture recordings into study notes walks through every step from capturing the voice recording to building flashcards and a practice exam.