Intel NPU based Speech To Text in any app at cursor
Offloads Whisper to Intel NPU so GPU stays free for other tasks.
Speech to text at cursor using NPU. (shortcut -> win+/)
Intel NPU offload frees GPU/CPU, but Windows-only with tiny hardware audience.
Windows users with Intel Core Ultra processors wanting local dictation
Superwhisper · MacWhisper · Whisper Desktop
Brings speech-to-text to any app at cursor via global hotkey.
- Converts spoken words to text and puts that text at your current keyboard's cursor location. Runs completely locally. - Keeps your GPU and CPU free by using Intel's NPU for running Speech to text conversion.
Offloads Whisper to Intel NPU so GPU stays free for other tasks.
Local Whisper + fine-tuned Qwen beats cloud STT on privacy, latency, cost.
Side-by-side model comparison eliminates guessing which speech engine fits your hardware.
EPUB-to-audiobook converter, but AudioBooks app and Findaway already handle this.
Local dictation with 420ms latency and sub-Whisper accuracy—actually ships, privacy-first.
Instant context-preserving definitions for AI-generated jargon—outpaces googling and ChatGPT threads.