Docs/AgentEyes/Recording
AgentEyes

Recording with AgentEyes

4 min read

AgentEyes records your screen and audio from named presets, keeps the results in a recording library, and can turn any recording into a transcript and a shareable write-up. It also types what you say into any app. This page covers what you can do today from the tray app; to script the same things, see the CLI reference.

Presets: pick one and record

A preset is a named capture profile, in the spirit of OBS scenes. A preset decides which monitor or region to capture, whether it records video, audio, or a single screenshot, and how the audio is handled - your microphone, the system (loopback) audio, or the two mixed together through a noise gate. You set a preset up once, then choose it and hit record.

  • Source. A whole monitor, or a region you draw.
  • Audio. Mic only, system audio only, or a mix of both. Mixing runs the audio through a noise gate, optional noise suppression, and voice leveling so the result is usable without editing.
  • Mode. Video, audio, or a screenshot.

The recording library

Recordings are saved under %USERPROFILE%\Videos\AgentEyes\, one folder per recording. The tray app lists your recent recordings so you can find, play, and act on them. Each recording folder holds the captured video or audio, any screenshots you took mid-recording, and - once you build it - the transcript.

Note
AgentEyes today is a record-when-you-choose tool: you pick a preset and start. The always-on rolling buffer - a recorder that is always capturing so you can reach back and keep a moment after the fact - is the product's larger goal and is still on the roadmap, not something you can rely on yet.

Turn a recording into a write-up

The walkthrough builder takes a recording and produces two things: a transcript of what was said, and a shareable HTML write-up that pairs the transcript with screenshots from the recording. The raw capture becomes something you can drop into a ticket, a document, or a message without editing video.

Note
Building the transcript uses DevThrottle's hosted Whisper through your signed-in account, so a recording's audio is sent to DevThrottle to be transcribed. The recording itself stays in your local library. Voice typing, below, is different - it runs on a local model.

Type with your voice, anywhere

Double-tap Ctrl in any application, speak, and the transcription is typed straight into whatever has focus. There is no browser tab and no cloud round-trip: dictation runs on a local Whisper model that loads once when AgentEyes starts. It is the fastest way to get a sentence into a field, a chat, or a prompt without touching the keyboard.

Tip
Voice typing shares its custom-dictionary corrections with the rest of DevThrottle, so names and terms it learns are fixed everywhere you dictate. See Voice.

Where to go next

To bring an existing video into the library, see Import a video. To caption a recording in another language, see Multilingual subtitles. To do any of this from a script, see the CLI reference and the Control API.