Glossary

Meeting recording glossary

Short, accurate definitions of the terms you run into around meeting recording and transcription. Each entry explains what the term means, why it matters, and how it connects to the way Autorec works.

All terms

AI meeting summary

An AI meeting summary is a short written overview of a meeting, generated automatically by a language model from the meeting's transcript.

Audio ducking

Audio ducking is the automatic lowering of one audio track's volume whenever another track becomes active.

Local-first software

Local-first software is software that keeps your data on your own device and works without depending on a remote server.

Loopback audio

Loopback audio is the sound a computer is playing back, captured as if it were a recording input.

Meeting recorder

A meeting recorder is software that captures the audio and video of a video call so the meeting can be reviewed, transcribed, or archived afterwards.

Meeting recording consent

Meeting recording consent is the agreement participants give to having a call or conversation recorded.

Meeting transcription

Meeting transcription is the process of converting the spoken audio of a meeting into a written text record.

Notetaker bot

A notetaker bot is an automated participant that joins a video call as a visible attendee to record, transcribe, and summarize the meeting.

On-device transcription

On-device transcription is speech-to-text conversion that runs entirely on your own computer, without uploading the audio to a remote server.

Screen recording

Screen recording is the capture of everything shown on a computer display as a video file.

Speaker diarization

Speaker diarization is the process of splitting an audio recording into segments and labelling which speaker is talking in each one.

SRT subtitle file

An SRT subtitle file is a plain-text file that pairs lines of text with start and end timestamps, so the text can be displayed in sync with a video.

Two-party consent

Two-party consent is a legal rule under which every participant in a conversation must agree before it may be recorded.

Voice activity detection

Voice activity detection (VAD) is a technique that identifies which parts of an audio stream contain speech and which are silence or background noise.

whisper.cpp

whisper.cpp is a C/C++ port of OpenAI's Whisper speech recognition model, designed to run speech-to-text transcription locally on ordinary hardware.

Window capture

Window capture is a recording method that records the contents of a single application window, rather than the whole display.

Record and transcribe your meetings locally

Autorec detects your Zoom, Teams, and Google Meet calls, records them to your own disk, and transcribes them on your machine. No bot joins the call, and nothing gets uploaded to the cloud.

Download Autorec