Update utils.py

utils.py

@@ -431,16 +431,19 @@ def transcribe_youtube_video(video_url: str) -> str:
 def generate_audio_mp3(text: str, speaker: str) -> str:
     """
     Calls Deepgram TTS with the text, returning a path to a temp MP3 file.
-    We also do some pre-processing for punctuation, abbreviations, numeric expansions, 
-    plus emotive expressions (ha, sigh, etc.).
+    Skips preprocessing for John and Jane to preserve natural pronunciation.
     """
     try:
         print(f"[LOG] Generating audio for speaker: {speaker}")
-        processed_text = _preprocess_text_for_tts(text, speaker)
+        # Skip preprocessing for John and Jane for natural pronunciation.
+        if speaker in ["John", "Jane"]:
+            processed_text = text
+        else:
+            processed_text = _preprocess_text_for_tts(text, speaker)
 
         deepgram_api_url = "https://api.deepgram.com/v1/speak"
         params = {
-            "model": "aura-asteria-en",  # female by default
+            "model": "aura-asteria-en",  # default female voice model
         }
         if speaker == "John":
             params["model"] = "aura-zeus-en"