Speech Recognition and Synthesis along with Offline support - Coqui STT and espeak

[karan-aithal]

Overview:

Coqui STT for Speech Recognition:

Coqui STT is an open-source speech recognition engine that can be run offline. We'll use it to capture speech from the microphone, convert it into text, and process the recognized commands.

Text-to-Speech (TTS):

Use Coqui TTS (or espeak for offline synthesis) to convert the text generated by Buzvis into spoken words.

Business Logic:

1. Capture microphone input.
2. Use Coqui STT to convert the spoken command into text.
3. Process the text, generate a response (either using AI or simple rules for now).
4. Use TTS to convert the response back to speech and play it back.

[karan-aithal]

buzvis-app/ ├── CMakeLists.txt ├── src/ │ ├── app/ │ │ ├── BuzvisApp.h │ │ ├── BuzvisApp.cpp │ ├── modules/ │ │ ├── SpeechRecognition.h # Speech Recognition logic using Coqui STT │ │ ├── SpeechRecognition.cpp │ │ ├── SpeechSynthesis.h # Text-to-Speech logic (Coqui TTS or espeak) │ │ ├── SpeechSynthesis.cpp │ └── ui/ ├── include/ └── resources/