Explaining something is often easier when you can point at it. VoxBee's screenshot smart paste lets you capture a screen region during dictation — then intelligently delivers both the image and your spoken text to the app you're working in.
How It Works
- Start dictating — Hold your hotkey to begin recording
- Capture a screenshot — While recording, drag to select a screen region
- Release and transcribe — VoxBee transcribes your speech and pairs it with the screenshot
- Smart paste — Both image and text are delivered to the frontmost app in the right format
Three Tiers of Smart Paste
VoxBee detects what app you're in and adjusts how it delivers the screenshot:
CLI Apps (Terminal, iTerm2, Warp)
Pastes the file path and your text. The temp file is preserved on disk so CLI agents and tools can read the image.
Rich Content Apps (Browsers, Slack, VS Code, Cursor, Codex)
Pastes the image first, waits briefly, then pastes your text. Both appear inline in the app.
Plain Text Apps (Everything Else)
Injects your text and leaves the screenshot on the clipboard so you can paste it manually with Cmd+V.
Use Cases
- Bug reports — Capture the error on screen, describe it with your voice, paste both into a ticket
- Code reviews — Screenshot the relevant code, dictate your feedback, drop it into Slack or a PR comment
- Documentation — Capture UI screenshots and narrate what they show
- Pair programming — Share visual context with spoken explanation in chat
Learn more about VoxBee Dictation or download VoxBee to try screenshot smart paste free for 14 days.