Update app.py

app.py

@@ -1,14 +1,18 @@
 import gradio as gr
 import os
 from groq import Groq
+import tempfile
+import shutil
+
 
 # Initialize the Groq client
 client = Groq(api_key=os.environ["keko"])
 
-def transcribe_audio(audio_file):
+
+def transcribe_and_save_audio(audio_file):
     if audio_file is None:
-        return "No audio file provided."
-    
+        return "No audio file provided.", None
+
     # Create a transcription of the audio file
     with open(audio_file, "rb") as file:
         transcription = client.audio.transcriptions.create(
@@ -19,15 +23,54 @@ def transcribe_audio(audio_file):
             temperature=0.0
         )
     
-    return transcription.text
+    # Save the audio file as MP3
+    mp3_file = tempfile.NamedTemporaryFile(delete=False, suffix=".mp3")
+    shutil.copy2(audio_file, mp3_file.name)
+    
+    return transcription.text, mp3_file.name
 
 # Create the Gradio interface
 iface = gr.Interface(
-    fn=transcribe_audio,
+    fn=transcribe_and_save_audio,
     inputs=gr.Audio(sources=["microphone", "upload"], type="filepath"),
-    outputs=gr.Textbox(label="Transcription", show_copy_button=True),
+    outputs=[
+        gr.Textbox(label="Transcription", show_copy_button=True),
+        gr.Audio(label="Recorded Audio (MP3)", format="mp3")
+    ],
     title="Audio Transcription with Groq",
-    description="Record audio or upload a file - speech-to-text."
+    description="Record audio or upload a file - speech-to-text. You can also download the recorded audio as MP3."
 )
+
 # Launch the interface
-iface.launch()
+iface.launch()
+
+
+
+
+
+# def transcribe_audio(audio_file):
+#     if audio_file is None:
+#         return "No audio file provided."
+    
+#     # Create a transcription of the audio file
+#     with open(audio_file, "rb") as file:
+#         transcription = client.audio.transcriptions.create(
+#             file=(audio_file, file.read()),
+#             model="whisper-large-v3",
+#             prompt="text may contain medical gastroenterology terms",
+#             response_format="json",
+#             temperature=0.0
+#         )
+    
+#     return transcription.text
+
+# # Create the Gradio interface
+# iface = gr.Interface(
+#     fn=transcribe_audio,
+#     inputs=gr.Audio(sources=["microphone", "upload"], type="filepath"),
+#     outputs=gr.Textbox(label="Transcription", show_copy_button=True),
+#     title="Audio Transcription with Groq",
+#     description="Record audio or upload a file - speech-to-text."
+# )
+# # Launch the interface
+# iface.launch()