using configuration url to do stuff now

Signed-off-by: Rishi <[email protected]>

config.py

@@ -45,6 +45,10 @@ class UpdateInfo:
 class Memory:
     context_limit: int
 
+@dataclass
+class Voice:
+    url: str
+
 @dataclass
 class DeviceConfig:
     user_info: UserInfo
@@ -53,6 +57,7 @@ class DeviceConfig:
     google_cloud_security_file: GoogleCloudSecurityFile
     update_info: UpdateInfo
     memory: Memory
+    voice: Voice
 
     @classmethod
     def from_dict(cls, data: dict):
@@ -64,7 +69,9 @@ def from_dict(cls, data: dict):
             api_limits=APILimits(**data['api_limits']),
             google_cloud_security_file=GoogleCloudSecurityFile(**data['google_cloud_security_file']),
             update_info=UpdateInfo(**data['update_info']),
-            memory=Memory(**data['memory'])
+            memory=Memory(**data['memory']),
+            voice=Voice(**data['voice']) 
+
         )
 
     def to_dict(self):
@@ -74,10 +81,13 @@ def to_dict(self):
             "api_limits": asdict(self.api_limits),
             "google_cloud_security_file": asdict(self.google_cloud_security_file),
             "update_info": asdict(self.update_info),
-            "memory": asdict(self.memory)
+            "memory": asdict(self.memory),
+            "voice": asdict(self.voice) 
+
         }
 
 
+
 def get_configuration(url: str, device_uuid: Union[str, None]) -> Union[str, DeviceConfig]:
     if device_uuid is None:
         return "No Device Set Yet!"

main.py

@@ -51,7 +51,6 @@ def increase_volume():
     'X-Device-Serial': get_serial_number()
 }
 
-tts = TextToSpeechPlayer()
 
 load_dotenv()
 
@@ -68,6 +67,11 @@ def increase_volume():
 # Configure Device etc
 configuration = get_configuration(BASE_URL, test_device_uuid)
 
+print(f"Line 71 : {configuration}")
+
+# sys.exit()
+tts = TextToSpeechPlayer(configuration.voice.url)
+
 MEMORY_CONTEXT = 0
 
 if isinstance(configuration, str):
@@ -215,7 +219,7 @@ async def process_input(recognized_text):
         # print(f"Response : {conversation}")
         display_controller.render_text_threaded_v2(speech)
         # await output_voice(speech)
-        tts.text_to_speech(speech, "output.mp3")
+        tts.play(speech, headers)
 
 
 def voice_filler():

voice.py

@@ -3,7 +3,7 @@
 import threading
 import time
 from tempfile import TemporaryFile
-
+import requests as r
 from google.cloud import texttospeech
 from gtts import gTTS
 from measure import timing
@@ -15,8 +15,9 @@
 
 
 class TextToSpeechPlayer:
-    def __init__(self):
+    def __init__(self, url):
         self.client = texttospeech.TextToSpeechClient()
+        self.url = url
 
     def synthesize_speech(self, text, output_filename):
         start_time = time.time()
@@ -84,6 +85,30 @@ def cues_to_audio_files(self, cue_dict, folder_name):
 
             print(f"Saved '{cue}' to {filepath}")
 
+
+    def play(self, text, headers):
+        # Make a request to the Django API endpoint to get synthesized audio
+        response = r.post(
+            self.url,
+            json={"text": text},
+            headers=headers,
+        )
+
+        # Check if the request was successful
+        if response.status_code == 200:
+            output_filename = "output.mp3"
+
+            # Write the audio data to a temporary file
+            with open(output_filename, "wb") as file:
+                file.write(response.content)
+
+            # Load and play the audio
+            self.load_and_play(output_filename)
+
+        else:
+            print(f"Failed to get audio. Status code: {response.status_code}. Message: {response.text}")
+
+
 @timing
 async def output_voicev2(text: str, expect_return=False):
     tts = gTTS(text, lang='en')