Record
Press your shortcut. Speak naturally. Dimmy captures every word with crystal clarity.
Dimmy sits on your screen. Press a key, speak, get text. That simple.
PRODUCT
A tiny pill sits at the edge of your screen. Unobtrusive. Waiting.
Press your hotkey. The pill expands. A waveform pulses with your voice.
Your words stream onto screen in real-time. AI transcribes every syllable.
Choose a style. Your text transforms. It's in your clipboard, ready to paste.
HOW IT WORKS
Press your shortcut. Speak naturally. Dimmy captures every word with crystal clarity.
AI transcribes in real-time. Six providers, one interface. Pick what works for you.
13 AI styles reshape your words instantly. Professional, creative, or completely unhinged.
PROVIDERS
Six AI providers. Swap anytime. Some are completely free.
Blazing-fast Whisper inference. Zero cost, zero compromise.
The gold standard. Whisper and GPT in one provider.
Enterprise-grade speech recognition with generous free tier.
Google's multimodal AI for powerful text enhancement.
Claude-powered enhancement. Thoughtful, nuanced text styling.
Access 100+ models through a single API. Ultimate flexibility.
STYLES
Same voice. Different vibes. Watch your words transform in real-time.
Hey team, I wanted to follow up on yesterday's meeting about the Q3 roadmap. I think we should prioritize the mobile app and maybe push the API redesign to Q4.
FEATURES
Windows. macOS. Linux. Same experience everywhere. No compromises, no platform-specific quirks. One app, three operating systems.
API keys stored in your OS keyring. Never in config files, never in plain text. Your credentials stay yours.
See your words appear as you speak. Live waveform visualization plus streaming text output.
Preprocessing pipeline filters silence and noise before it hits the AI. No phantom words from empty audio.
Free as in freedom. Community-driven development, transparent codebase, no telemetry. Fork it, improve it, make it yours.