This project contains a Flask Web Server that hosts a web page for recording voice input via recorder.js. After recording voice input, the webpage sends the audio to the Flask Server. When received, the server invokes the SpeechRecognition library to transcribe speech. The Speech-To-Text result is then printed in the Flask Development console.
index.html
and main.js
is derived from blog.addpipe.com.
- Download or Clone project
- Setup and Activate Python Venv
- Install dependencies using
python -m pip install -r requirements.txt
- Set Flask Current App to webapp.py:
- PowerShell:
$env:FLASK_APP='webapp'
- PowerShell:
- Run Flask App:
python -m flask run