From 3cdde2d49cba4b43045ebef7f16236fed3a4acc9 Mon Sep 17 00:00:00 2001
From: meta-fx <nmd.devs.1@gmail.com>
Date: Tue, 11 Apr 2023 08:15:58 -0500
Subject: [PATCH] Resolved conflicts in config.py and speak.py

---
 scripts/config.py |  7 ++----
 scripts/speak.py  | 60 ++++++++++++++++++++++++++++++-----------------
 2 files changed, 40 insertions(+), 27 deletions(-)

diff --git a/scripts/config.py b/scripts/config.py
index f636da7dfd..cdf0287c4b 100644
--- a/scripts/config.py
+++ b/scripts/config.py
@@ -33,7 +33,7 @@ class Config(metaclass=Singleton):
 
     def __init__(self):
         """Initialize the Config class"""
-        self.debug = False
+        self.debug_mode = False
         self.continuous_mode = False
         self.speak_mode = False
 
@@ -92,9 +92,6 @@ class Config(metaclass=Singleton):
         """Set the speak mode value."""
         self.speak_mode = value
 
-    def set_debug_mode(self, value: bool):
-        self.debug_mode = value
-
     def set_fast_llm_model(self, value: str):
         """Set the fast LLM model value."""
         self.fast_llm_model = value
@@ -137,4 +134,4 @@ class Config(metaclass=Singleton):
 
     def set_debug_mode(self, value: bool):
         """Set the debug mode value."""
-        self.debug = value
\ No newline at end of file
+        self.debug_mode = value
\ No newline at end of file
diff --git a/scripts/speak.py b/scripts/speak.py
index 2464c62596..bf5c6034fa 100644
--- a/scripts/speak.py
+++ b/scripts/speak.py
@@ -4,6 +4,8 @@ import requests
 from config import Config
 cfg = Config()
 import gtts
+import threading
+from threading import Lock, Semaphore
 
 
 # TODO: Nicer names for these ids
@@ -14,6 +16,9 @@ tts_headers = {
     "xi-api-key": cfg.elevenlabs_api_key
 }
 
+mutex_lock = Lock() # Ensure only one sound is played at a time
+queue_semaphore = Semaphore(1) # The amount of sounds to queue before blocking the main thread
+
 def eleven_labs_speech(text, voice_index=0):
     """Speak text using elevenlabs.io's API"""
     tts_url = "https://api.elevenlabs.io/v1/text-to-speech/{voice_id}".format(
@@ -23,10 +28,11 @@ def eleven_labs_speech(text, voice_index=0):
         tts_url, headers=tts_headers, json=formatted_message)
 
     if response.status_code == 200:
-        with open("speech.mpeg", "wb") as f:
-            f.write(response.content)
-        playsound("speech.mpeg")
-        os.remove("speech.mpeg")
+        with mutex_lock:
+            with open("speech.mpeg", "wb") as f:
+                f.write(response.content)
+            playsound("speech.mpeg", True)
+            os.remove("speech.mpeg")
         return True
     else:
         print("Request failed with status code:", response.status_code)
@@ -39,10 +45,11 @@ def brian_speech(text):
     response = requests.get(tts_url)
 
     if response.status_code == 200:
-        with open("speech.mp3", "wb") as f:
-            f.write(response.content)
-        playsound("speech.mp3")
-        os.remove("speech.mp3")
+        with mutex_lock:
+            with open("speech.mp3", "wb") as f:
+                f.write(response.content)
+            playsound("speech.mp3")
+            os.remove("speech.mp3")
         return True
     else:
         print("Request failed with status code:", response.status_code)
@@ -51,24 +58,33 @@ def brian_speech(text):
 
 def gtts_speech(text):
     tts = gtts.gTTS(text)
-    tts.save("speech.mp3")
-    playsound("speech.mp3")
-    os.remove("speech.mp3")
+    with mutex_lock:
+        tts.save("speech.mp3")
+        playsound("speech.mp3", True)
+        os.remove("speech.mp3")
 
 def macos_tts_speech(text):
     os.system(f'say "{text}"')
 
 def say_text(text, voice_index=0):
-    if not cfg.elevenlabs_api_key:
-        if cfg.use_mac_os_tts == 'True':
-            macos_tts_speech(text)
-        elif cfg.use_brian_tts == 'True':
-            success = brian_speech(text)
-            if not success:
+    
+    def speak():
+        if not cfg.elevenlabs_api_key:
+            if cfg.use_mac_os_tts == 'True':
+                macos_tts_speech(text)
+            elif cfg.use_brian_tts == 'True':
+                success = brian_speech(text)
+                if not success:
+                    gtts_speech(text)
+            else:
                 gtts_speech(text)
         else:
-            gtts_speech(text)
-    else:
-        success = eleven_labs_speech(text, voice_index)
-        if not success:
-            gtts_speech(text)
\ No newline at end of file
+            success = eleven_labs_speech(text, voice_index)
+            if not success:
+                gtts_speech(text)
+        
+        queue_semaphore.release()
+
+    queue_semaphore.acquire(True)
+    thread = threading.Thread(target=speak)
+    thread.start()
\ No newline at end of file