Nikorasu/LiveWhisper
A nearly-live implementation of OpenAI's Whisper, using sounddevice. Requires existing Whisper install.
Streams audio through volume and frequency thresholds to detect speech boundaries, then batches segments to Whisper for sentence-level transcription with minimal latency. Also includes a voice assistant layer (`assistant.py`) that adds wake-word detection, media controls, and task execution (weather, Wikipedia, math) via text-to-speech responses using tts and web APIs.
360 stars. No commits in the last 6 months.
Stars
360
Forks
49
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
Softcatala/whisper-ctranslate2
Whisper command line client compatible with original OpenAI client based on CTranslate2.
collabora/WhisperLive
A nearly-live implementation of OpenAI's Whisper.
kurianbenoy/whisper_normalizer
A python package for whisper normalizer
Kieirra/murmure
Fully local, private and cross platform Speech-to-Text with LLM Post-processing
pavelzbornik/whisperX-FastAPI
FastAPI service on top of WhisperX