IBM Watson TTS and STT using computer mic and speakers (no audio files) + enhancements!

Currently, IBM Watson API only allows you to work with audio files on your computer to implement Speech To Text and Text to Speech.

🔵 Now you have WARVIS (Watson + JARVIS = ¯ \ _ (ツ) _ / ¯) 🔵

WARVIS works directly with your microphone and provides the functionality of IBM Watson TTS without having to store audio files of your voice recordings.

🔵 WARVIS detects loudness levels when recording and 'waits' until you start speaking 🔵

• You are able to customise the loudness threshold of your voice, so WARVIS knows when to start 'listening'
• You can also change the number of seconds to wait after you finish speaking, so you are not interrupted when making pauses between sentences

🔵 Text To Speech has never been that easy. No audio files at all! 🔵

• Just type in the words that you would like your computer to 'say' and it will do it in a matter of seconds, without having to save an audio file of the generated voice.

Instructions

• Go to IBM Cloud website, create credentials for TTS and STT (it's free!)
• Insert them into main.py

WARNING

The program might take some time for the initial launch, please be patient!