Speech to text and Text to speech function.

app.py

@@ -4,7 +4,7 @@ import MAIAI
 
 # from deep_translator import GoogleTranslator
 
-import speech_recognition as sr
+# import speech_recognition as sr
 # import assemblyai as aai
 
 # import pyttsx3
@@ -170,30 +170,30 @@ def gtts(input_text,language='English'):
 #     transcript = transcriber.transcribe(audio_file_path)
 #     return transcript.text
 
-def google_speech_to_text(audio_file_path):
-    if audio_file_path:
-        recognizer = sr.Recognizer()
-        with sr.AudioFile(audio_file_path) as source:
-            audio_data = recognizer.record(source)
-            try:
-                text = recognizer.recognize_google(audio_data)
-                return text
-            except sr.UnknownValueError:
-                return "Google Speech Recognition could not understand audio"
-            except sr.RequestError as e:
-                return f"Could not request results from Google Speech Recognition service; {e}"
+# def google_speech_to_text(audio_file_path):
+#     if audio_file_path:
+#         recognizer = sr.Recognizer()
+#         with sr.AudioFile(audio_file_path) as source:
+#             audio_data = recognizer.record(source)
+#             try:
+#                 text = recognizer.recognize_google(audio_data)
+#                 return text
+#             except sr.UnknownValueError:
+#                 return "Google Speech Recognition could not understand audio"
+#             except sr.RequestError as e:
+#                 return f"Could not request results from Google Speech Recognition service; {e}"
 
 
-# def openai_speech_to_text(audio_file_path):
-#     if audio_file_path:
-#         client = OpenAI()
-#         audio_file= open(audio_file_path, "rb")
-#         transcription = client.audio.transcriptions.create(
-#             model="whisper-1", 
-#             response_format="text",
-#             file=audio_file
-#         )
-#         return transcription
+def openai_speech_to_text(audio_file_path):
+    if audio_file_path:
+        client = OpenAI()
+        audio_file= open(audio_file_path, "rb")
+        transcription = client.audio.transcriptions.create(
+            model="whisper-1", 
+            response_format="text",
+            file=audio_file
+        )
+        return transcription
 
 def chat(text, history, native_language, language, persona, tone = "Casual", model = "gpt-4o-mini"):
     
@@ -274,7 +274,7 @@ You MUST give your feedback in {native_language}.
 
 # Gradio Custom Chatbot -------------------------------------------------------
 
-with gr.Blocks(fill_height=True) as demo:
+with gr.Blocks(fill_height=True, theme=Base()) as demo:
     
     chatbot = gr.Chatbot(
         elem_id="chatbot",
@@ -286,7 +286,7 @@ with gr.Blocks(fill_height=True) as demo:
         
         chat_input = gr.Textbox(interactive=True, scale=8,
                             inputs=[gr.components.Audio(sources="microphone", type="filepath", label="Speak or upload audio")],
-                            value=google_speech_to_text)
+                            value=openai_speech_to_text)
         submit_button = gr.Button("Submit", scale=1)
     
     with gr.Row():