Powerful Features.
Zero Bloat.
VibeVox is designed for power users who need distinct control over their privacy, latency, and quality.
Live Typing
Dictate and watch the text type itself into your app in real time, with a final polish when you stop. Prefer the classic way? The regular end-of-recording mode is always there.
Global Hotkey Control
Press your configured global hotkey anywhere in Windows to start/stop dictation, hold it down like a walkie-talkie (push-to-talk), or let auto mode tell a tap from a hold. No need to switch windows — the app floats on top of your work.
Private by Default
Your speech is transcribed locally with the NVIDIA Parakeet engine, running on your CPU. Nothing is sent to the cloud unless you explicitly turn on AI features.
Multilingual, Offline
Parakeet auto-detects and transcribes 25 European languages entirely on your device. Norwegian (Bokmål & Nynorsk) is available through an optional on-demand NB-Whisper pack.
AI: Translate & Rewrite
Bring your own key for OpenAI, Anthropic, Google Gemini, DeepSeek, Groq, Mistral, OpenRouter, YandexGPT — or any OpenAI-compatible custom endpoint. Translate your dictation live, select text anywhere and rewrite it by voice — or select nothing, and your dictation arrives written clean. Your key stays on your machine.
Built for Workflow
Custom hotkeys (keyboard chords, a double-tap modifier, or mouse buttons), a full audio panel with mic picker, sensitivity and a live level meter, noise reduction, a searchable transcription history, and an on-demand Norwegian language pack.
Smart Injection
VibeVox types text directly into your active application. If you switch windows mid-dictation, the text lands safely on your clipboard instead of the wrong app. Fine-tune the output with formatting toggles — like a lowercase first letter or trimming the final period.
25 languages, fully offline
Parakeet auto-detects the language and transcribes it entirely on your device. No cloud, no account — your voice never leaves the machine.
Optional packNorwegian? Also covered.
Bokmål and Nynorsk run through NB-Whisper Small — a model by the National Library of Norway. VibeVox downloads it once (~670 MB) right from Settings, and it works fully offline too.
Beyond the list: AI translation
With AI translate enabled, your dictation can be translated on the fly to virtually any language your AI provider understands — you speak one language, the text arrives in another.
Technical Specifications
Under the Hood: Next-Gen Architecture
Token-and-Duration Transducer (TDT)
Unlike traditional RNN-Ts that predict one token at a time, our TDT architecture jointly predicts both the token and its duration. This allows the model to skip silence and redundant frames during inference, drastically reducing compute time.
- Joint Token & Duration Prediction
- Skip-Frame Inference Acceleration
FastConformer with 8x Subsampling
Built on the Conformer architecture but optimized for speed. It uses an 8x downsampling factor to process audio frames more efficiently, combining the global context of Transformers with the local feature extraction of CNNs.
- 8x Downsampling Factor
- Runs entirely on CPU — no GPU required