Nikorasu/LiveWhisper

A nearly-live implementation of OpenAI's Whisper, using sounddevice. Requires existing Whisper install.

47
/ 100
Emerging

This project offers two main tools. The first transcribes spoken audio from your microphone into text, outputting it sentence-by-sentence as you speak. The second is a voice-activated assistant that responds to commands and questions, similar to Siri or Alexa. It's designed for anyone needing near real-time dictation or a hands-free voice interface for basic tasks and media control.

360 stars. No commits in the last 6 months.

Use this if you need to quickly get spoken words typed out as you say them, or if you want a basic voice assistant to control media, get weather updates, or perform simple searches.

Not ideal if you require highly complex voice commands, deep integration with other software, or enterprise-grade accuracy for critical applications without custom setup.

dictation voice-assistant transcription hands-free-control productivity
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

360

Forks

49

Language

Python

License

MIT

Last pushed

Jul 20, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/Nikorasu/LiveWhisper"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.