voice dictation for any text field in your OS
A tool that converts your voice to text using your local GPU.
The premise is simple: speaking is faster than typing. This project allows you to dictate in any application without depending on cloud services.
- local-first: your audio never leaves your machine
- modular: started as a script, now it's an app with separated responsibilities
- gpu-powered: transcription speed using WHISPER locally
Two global keyboard shortcuts:
| script | function |
|---|---|
v2m-toggle.sh |
records → transcribes → copies to clipboard |
v2m-llm.sh |
takes text from clipboard → refines it with LLM → replaces it |
All technical info is in /docs (consolidated in Spanish):
flowchart LR
A[🎤 record] --> B{whisper}
B --> C[📋 clipboard]
flowchart LR
A[📋 copy] --> B{LLM}
B --> C[📋 replace]
if you don't see the diagrams, you need a mermaid extension
This project is licensed under the GNU General Public License v3.0 - see the LICENSE file for more details.