How Fluesta works

Fluesta turns spoken language into ready-to-use text — in any app where you can type.

The flow in 5 steps

1. Hold hotkey  →  2. Speak  →  3. Cloud transcription
       ↓                                        ↓
5. Paste  ←  4. AI correction + glossary  ←  Audio

1. Start recording

Hold your dictation hotkey — on macOS the Fn/Globe key, on Windows Ctrl + Space. Fluesta shows a recording indicator near the cursor. Release to end recording.

2. Send audio to the cloud

The recording is sent encrypted to Fluesta’s EU servers and transcribed there. There is no offline mode — processing happens in the cloud.

3. Capture context

Fluesta optionally captures context from your active app (window title, selected text, surrounding text). This improves AI correction without extra configuration.

4. AI correction & glossary

When cloud correction is enabled, Fluesta cleans up grammar, punctuation, and formatting. Your glossary (personal and optionally team) feeds into correction — proper names and domain terms are preferred.

5. Insert text

With auto-paste, Fluesta inserts text via simulated Cmd+V / Ctrl+V into the active field. If auto-paste is off or the target app blocks paste, text goes to the clipboard.

Voice commands (edit selection)

When you select text and then hold the hotkey, Fluesta enters command mode: your speech transforms the selection (e.g. “make this shorter”) instead of appending new text.

Privacy & EU hosting

Fluesta is designed EU-first and GDPR-compliant:

Audio is processed for transcription and not stored permanently
Processing on EU infrastructure
Local transcription history stays on your device

More details in our privacy policy.