Why This Matters
Jexxa is a new on-device dictation tool that transcribes speech to text locally, appealing to privacy-conscious users and professionals who need fast, offline voice input without sending audio to the cloud. Its emphasis on speed, adaptive learning of custom vocabulary, and simple voice commands for corrections could make dictation more practical for everyday work across any application.
Key Takeaways
- Runs entirely on-device, so no audio or transcripts are uploaded, addressing privacy concerns common with cloud-based dictation tools.
- Claims very low latency (transcription within about a fifth of a second), making it usable for real-time thinking and typing without per-minute costs.
- Includes adaptive learning for names/jargon and simple voice commands (like 'JX minus one') to undo or correct dictated text, plus a live preview for immediate feedback.
The model is on your disk. Hold a key, speak, and the words appear where your cursor already is â in any app that takes text.
đ Nothing is uploaded No audio, no transcript. What does leave is small and listed in the privacy policy: your subscription check, update checks, and diagnostics you can turn off.
⥠Fast enough to think in Most dictations are typed within a fifth of a second of letting go of the key. No queue, no per-minute cost.
âī¸ It learns your words Names and jargon it gets wrong once, it gets right after you fix it. It tells you what it learned, and you can undo it.
âŠī¸ Take back what you said Say JX minus one to remove the last line, JX minus two for two, JX clear for the lot.
đ See it as you speak A live preview while you talk, so you know it is hearing you.
GoKawiil