LocalStt ၊▹

A module for speech to text & transcription stuff.

Core modules:

• Pyaudio(Pa_INT16): recording

• WhisperModel(CPU_INT8): transcription.

PowerShell is used here to improve the cli experience (setup, environment and updates).

📦 Installation

Install-Module LocalSTT

🗒 Usage

Import-Module LocalSTT

Record-Audio -o output.wav

Transcribe-Audio output.wav

NOTES

• currently Works with Python <= 3.12 : faster-whisper/issues/1238

🧾 License

This project is licensed under the WTFPL License.