From a292f571cb801eb4deb606499e9b250c67ce339f Mon Sep 17 00:00:00 2001
From: retoor <retoor@molodetz.nl>
Date: Sat, 18 Jan 2025 10:02:13 +0100
Subject: [PATCH] Update.

---
 gcloud.py        |  2 +-
 play.py          | 24 +++++++++++++++++-------
 requirements.txt |  1 +
 tts.py           | 27 ++++++++++++++++++++-------
 4 files changed, 39 insertions(+), 15 deletions(-)

diff --git a/gcloud.py b/gcloud.py
index 8390181..3b8ee1a 100644
--- a/gcloud.py
+++ b/gcloud.py
@@ -122,4 +122,4 @@ async def main():
 
 
 if __name__ == '__main__':
-    asyncio.run(main())
\ No newline at end of file
+    asyncio.run(main())
diff --git a/play.py b/play.py
index b89f4a5..1fc1096 100644
--- a/play.py
+++ b/play.py
@@ -29,12 +29,21 @@ import functools
 import os
 import subprocess
 import sys
+import pygame 
+
+
+
 
-@functools.cache
-def get_py_audio():
-    return pyaudio.PyAudio()
 
 def play_audio(filename):
+    pygame.mixer.init()
+    pygame.mixer.music.load(filename)
+    pygame.mixer.music.play()
+    while pygame.mixer.music.get_busy():
+        pygame.time.Clock().tick(10)
+
+
+def play_audio2(filename):
     ffmpeg_cmd = [
         "ffmpeg",
         "-i", filename,
@@ -45,9 +54,9 @@ def play_audio(filename):
     ]
     process = subprocess.Popen(ffmpeg_cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, bufsize=10**6)
 
-    py_audio = get_py_audio()
-    stream = py_audio.open(
-        format=py_audio.get_format_from_width(2),
+    p = pyaudio.PyAudio()
+    stream = p.open(
+        format=p.get_format_from_width(2),
         channels=2,
         rate=44100,
         output=True
@@ -62,5 +71,6 @@ def play_audio(filename):
     finally:
         stream.stop_stream()
         stream.close()
+        p.terminate()
         process.stdout.close()
-        process.wait()
\ No newline at end of file
+        process.wait()
diff --git a/requirements.txt b/requirements.txt
index 5967d96..f4d3b6f 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -3,3 +3,4 @@ SpeechRecognition
 google-cloud-speech
 google-cloud-texttospeech
 google-auth
+pygame
diff --git a/tts.py b/tts.py
index fffdaf6..f04c309 100644
--- a/tts.py
+++ b/tts.py
@@ -33,23 +33,22 @@ import gcloud
 
 molodetz = ServerProxy("https://api.molodetz.nl/rpc")
 
-async def main():
+def listen():
     recognizer = sr.Recognizer()
-
     with sr.Microphone() as source:
         print("Adjusting to surroundings for a five seconds.")
-        recognizer.adjust_for_ambient_noise(source, duration=5)
 
 
+        
+        #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
-                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)
+                source = None 
+                recognizer = None 
+                return text
             except sr.WaitTimeoutError:
                 continue
             except sr.UnknownValueError:
@@ -57,6 +56,20 @@ async def main():
             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())