ai_speech_research_papers/tts.py

# Written by retoor@molodetz.nl

# This script listens to audio input via a microphone, recognizes speech using the Google API, sends the recognized text to a server for processing, and uses Google Cloud to convert the server response to speech.

# Imports:
# - speech_recognition: For speech recognition functionality.
# - xmlrpc.client: To communicate with a remote server using the XML-RPC protocol.
# - gcloud: Presumably for Google Cloud services, though this requires clarification or specific library inclusion.

# MIT License
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
# 
# The above copyright notice and this permission notice shall be included in all
# copies or substantial portions of the Software.
# 
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.

import speech_recognition as sr
from xmlrpc.client import ServerProxy
import gcloud

molodetz = ServerProxy("https://api.molodetz.nl/rpc")

def listen():
    recognizer = sr.Recognizer()
    with sr.Microphone() as source:
        print("Adjusting to surroundings for a five seconds.")


        
        #recognizer.non_speaking_duration = 60*60
        while True:
            print("Listening...")
            try:
                audio_data = recognizer.listen(source, timeout=10)
                text = recognizer.recognize_google(audio_data, language="nl-NL") #en-US
                source = None 
                recognizer = None 
                return text
            except sr.WaitTimeoutError:
                continue
            except sr.UnknownValueError:
                continue
            except sr.RequestError:
                continue




async def main():


    #recognizer.adjust_for_ambient_noise(source, duration=5)
    while True:
        text = listen()
        print(f"You said:\n\t{text}")
        response_llm = molodetz.gpt4o_mini(text)
        print(f"GPT4o mini said:\n\t{response_llm}")
        await gcloud.tts(response_llm)

if __name__ == "__main__":
    import asyncio
    asyncio.run(main())