Whisperio

Whisperio

Press a hotkey, speak, and your words land wherever the cursor is. Cloud or fully offline with local Whisper models.

Download
Terminal
Ctrl Shift Space
Listening...
~/project agent start
AI Agent v3.2 ready
Listening for input...
> refactor the auth module to use JWT tokens
Done. Updated 3 files.
Notepad
Ctrl Shift Space
Listening...
Project kickoff - Q2 planning

Browser
Ctrl Shift Space
search.example.com
Listening...
1
Press hotkey
From anywhere
2
Speak
Whisperio listens
3
Stop
Press hotkey again
4
Transcribe
Cloud or local
5
Auto-paste
Text at cursor

Features

What's inside.

Cloud STT Providers

OpenAI gpt-4o-transcribe or ElevenLabs Scribe v2. Set up a priority chain — if one fails, the next kicks in automatically.

Offline Local Models

Download Whisper GGML models from HuggingFace in one click. Start a local whisper.cpp server directly from the app. Full privacy, no cloud.

Global Hotkey

System-wide shortcut that works from any app. Game-style key recorder in settings — press any combination you want.

Auto-Paste

Transcribed text is pasted directly into the focused text field via simulated Ctrl+V. No copy-paste needed.

Dictate & Send

Separate hotkey that presses Enter after pasting. Speak into Slack, Discord, or any chat — your message sends automatically.

Output Recording

Capture and transcribe system audio — meetings, calls, video playback. Separate hotkey for output recording.

AI Post-Processing

Optional LLM pass after transcription to fix misrecognized technical terms. Uses your custom vocabulary list for corrections.

Recording History

All recordings saved to disk with timestamps. Browse, replay audio, view transcriptions, re-process with different settings.

Multi-Monitor Overlay

Minimal floating pill with live waveform appears on every connected display. Shows recording state without stealing focus.

Dark & Light Themes

Toggle between dark and light mode. System tray integration — runs in the background, launches at startup.

Run from Source

No installer needed. Clone the repo, run start.ps1 or npm run dev. Works on Windows, macOS, and Linux.

Open Source

MIT licensed. Full source on GitHub. Inspect the code, contribute, fork it. No telemetry, no tracking.