Update app.py via AI Editor

app.py

@@ -54,7 +54,17 @@ if not grok_api_key:
 server = flask.Flask(__name__)
 app = dash.Dash(__name__, server=server, external_stylesheets=[dbc.themes.BOOTSTRAP], suppress_callback_exceptions=True)
 
-session_data = defaultdict(lambda: {"audio_path": None, "transcript": None, "minutes": None, "temp_dir": None, "original_filename": None})
+session_data = defaultdict(lambda: {
+    "audio_path": None,
+    "transcript": None,
+    "minutes": None,
+    "temp_dir": None,
+    "original_filename": None,
+    "diarized_transcript": None,
+    "diarization_done": False,
+    "advanced_diarized_transcript": None,
+    "preview_mode": "auto"
+})
 session_locks = defaultdict(threading.Lock)
 
 def get_session_dir(session_id):
@@ -153,6 +163,186 @@ def transcribe_audio(file_path):
         logging.error(f"An unexpected error occurred during transcription: {e}")
         return f"Error during transcription: An unexpected error occurred."
 
+def diarize_transcript_ai(transcript, model_name, session_id):
+    logging.info(f"Starting AI diarization using {model_name} for session {session_id}")
+    if not transcript or "Error:" in transcript:
+        return "Error: Cannot diarize invalid or missing transcript."
+    prompt = (
+        "You are given a transcript of a conversation or meeting. "
+        "Please analyze the text and assign speaker turns as Speaker 1, Speaker 2, etc. "
+        "If a person introduces themselves by name, try to use their name as the speaker label. "
+        "Otherwise, assign speakers based on changes in voice, speech patterns, or cues in the transcript. "
+        "Format the output as alternating lines, each starting with the speaker label, for example:\n"
+        "Speaker 1: Hello and welcome.\n"
+        "Speaker 2: Thank you. My name is Alex.\n"
+        "Alex: I have a question about...\n"
+        "Speaker 1: Please go ahead.\n"
+        "If unsure, use Speaker 1, Speaker 2, etc. Do not invent content.\n\n"
+        f"Transcript:\n{transcript}\n\n"
+        "Diarized Transcript:"
+    )
+    with session_locks[session_id]:
+        try:
+            if model_name == 'openai':
+                if not openai.api_key: return "Error: OpenAI API key not configured."
+                client = openai.OpenAI()
+                response = client.chat.completions.create(
+                    model="gpt-3.5-turbo",
+                    messages=[
+                        {"role": "system", "content": "You are a professional assistant for meeting AI diarization."},
+                        {"role": "user", "content": prompt}
+                    ],
+                    timeout=120
+                )
+                logging.info(f"OpenAI diarization successful for session {session_id}")
+                return response.choices[0].message.content
+            elif model_name == 'gemini':
+                if not genai: return "Error: Google Gemini API not configured or key missing."
+                model = genai.GenerativeModel('gemini-1.5-flash-latest')
+                response = model.generate_content(
+                    prompt,
+                    request_options={'timeout': 120}
+                )
+                logging.info(f"Gemini diarization successful for session {session_id}")
+                if response.parts:
+                     return response.text
+                else:
+                     logging.warning(f"Gemini response blocked or empty for diarization for session {session_id}. Reason: {response.prompt_feedback}")
+                     return f"Error: Gemini response blocked or empty. Reason: {response.prompt_feedback}"
+            elif model_name == 'anthropic':
+                 if not anthropic: return "Error: Anthropic API not configured or key missing."
+                 response = anthropic.messages.create(
+                     model="claude-3-5-haiku-20241022",
+                     max_tokens=2000,
+                     messages=[
+                         {
+                             "role": "user",
+                             "content": prompt
+                         }
+                     ],
+                     timeout=120
+                 )
+                 logging.info(f"Anthropic diarization successful for session {session_id}")
+                 if response.content and isinstance(response.content, list) and hasattr(response.content[0], 'text'):
+                     return response.content[0].text
+                 else:
+                     logging.error(f"Could not extract content from Anthropic response (diarization): {response}")
+                     return "Error: Could not extract content from Anthropic response."
+            elif model_name == 'grok':
+                if not grok_api_key: return "Error: Grok API key (via Groq) not configured."
+                groq_url = "https://api.groq.com/openai/v1/chat/completions"
+                headers = {
+                    "Authorization": f"Bearer {grok_api_key}",
+                    "Content-Type": "application/json"
+                }
+                data = {
+                     "model": "grok-3-mini-fast-beta",
+                     "messages": [
+                        {"role": "system", "content": "You are a professional assistant for meeting AI diarization."},
+                        {"role": "user", "content": prompt}
+                        ],
+                     "max_tokens": 2000,
+                     "temperature": 0.7
+                }
+                response = requests.post(groq_url, headers=headers, json=data, timeout=120)
+                response.raise_for_status()
+                logging.info(f"Groq ({data['model']}) diarization successful for session {session_id}")
+                return response.json()["choices"][0]["message"]["content"]
+            else:
+                logging.warning(f"Invalid model selection for diarization: {model_name}")
+                return "Error: Invalid model selection"
+        except Exception as e:
+            logging.error(f"Error diarizing transcript with {model_name} for session {session_id}: {e}", exc_info=True)
+            return f"Error diarizing transcript using {model_name}: An unexpected error occurred."
+
+def advanced_diarize_transcript_ai(transcript, model_name, session_id):
+    logging.info(f"Starting advanced AI diarization using {model_name} for session {session_id}")
+    if not transcript or "Error:" in transcript:
+        return "Error: Cannot diarize invalid or missing transcript."
+    prompt = (
+        "Analyze the given transcript to identify distinct speakers without labeled identifiers. "
+        "Create unique speaker embeddings based on individual speech patterns, vocabulary choices, and linguistic styles. "
+        "Examine the context and content of each utterance to detect likely speaker changes. "
+        "Recognize typical conversation structures and turn-taking behaviors to differentiate between speakers. "
+        "Finally, use topic modeling to identify shifts in subject matter and areas of expertise, associating certain topics with specific speakers. "
+        "Based on this analysis, assign speaker labels (e.g., Speaker 1, Speaker 2, name if given) to each utterance in the transcript.\n\n"
+        f"Transcript:\n{transcript}\n\n"
+        "Diarized Transcript:"
+    )
+    with session_locks[session_id]:
+        try:
+            if model_name == 'openai':
+                if not openai.api_key: return "Error: OpenAI API key not configured."
+                client = openai.OpenAI()
+                response = client.chat.completions.create(
+                    model="gpt-3.5-turbo",
+                    messages=[
+                        {"role": "system", "content": "You are a professional assistant for meeting AI diarization."},
+                        {"role": "user", "content": prompt}
+                    ],
+                    timeout=120
+                )
+                logging.info(f"OpenAI advanced diarization successful for session {session_id}")
+                return response.choices[0].message.content
+            elif model_name == 'gemini':
+                if not genai: return "Error: Google Gemini API not configured or key missing."
+                model = genai.GenerativeModel('gemini-1.5-flash-latest')
+                response = model.generate_content(
+                    prompt,
+                    request_options={'timeout': 120}
+                )
+                logging.info(f"Gemini advanced diarization successful for session {session_id}")
+                if response.parts:
+                     return response.text
+                else:
+                     logging.warning(f"Gemini response blocked or empty for advanced diarization for session {session_id}. Reason: {response.prompt_feedback}")
+                     return f"Error: Gemini response blocked or empty. Reason: {response.prompt_feedback}"
+            elif model_name == 'anthropic':
+                 if not anthropic: return "Error: Anthropic API not configured or key missing."
+                 response = anthropic.messages.create(
+                     model="claude-3-5-haiku-20241022",
+                     max_tokens=2000,
+                     messages=[
+                         {
+                             "role": "user",
+                             "content": prompt
+                         }
+                     ],
+                     timeout=120
+                 )
+                 logging.info(f"Anthropic advanced diarization successful for session {session_id}")
+                 if response.content and isinstance(response.content, list) and hasattr(response.content[0], 'text'):
+                     return response.content[0].text
+                 else:
+                     logging.error(f"Could not extract content from Anthropic response (advanced diarization): {response}")
+                     return "Error: Could not extract content from Anthropic response."
+            elif model_name == 'grok':
+                if not grok_api_key: return "Error: Grok API key (via Groq) not configured."
+                groq_url = "https://api.groq.com/openai/v1/chat/completions"
+                headers = {
+                    "Authorization": f"Bearer {grok_api_key}",
+                    "Content-Type": "application/json"
+                }
+                data = {
+                     "model": "grok-3-mini-fast-beta",
+                     "messages": [
+                        {"role": "system", "content": "You are a professional assistant for meeting AI diarization."},
+                        {"role": "user", "content": prompt}
+                        ],
+                     "max_tokens": 2000,
+                     "temperature": 0.7
+                }
+                response = requests.post(groq_url, headers=headers, json=data, timeout=120)
+                response.raise_for_status()
+                logging.info(f"Groq ({data['model']}) advanced diarization successful for session {session_id}")
+                return response.json()["choices"][0]["message"]["content"]
+            else:
+                logging.warning(f"Invalid model selection for advanced diarization: {model_name}")
+                return "Error: Invalid model selection"
+        except Exception as e:
+            logging.error(f"Error in advanced diarization with {model_name} for session {session_id}: {e}", exc_info=True)
+            return f"Error advanced diarizing transcript using {model_name}: An unexpected error occurred."
+
 def generate_minutes_ai(transcript, model_name, session_id):
     logging.info(f"Generating minutes using {model_name} for session {session_id}")
     if not transcript or "Error:" in transcript:
@@ -275,87 +465,112 @@ app.layout = dbc.Container([
     dcc.Download(id="download-transcript"),
     dcc.Download(id="download-audio"),
     dcc.Download(id="download-minutes"),
+    dcc.Download(id="download-diarized"),
     dbc.Row([
-        dbc.Col(html.H1("AI Meeting Assistant", className="text-center my-4"), width=12)
-    ]),
-    dbc.Row([
-        dbc.Col(dbc.Card(
-            dbc.CardBody([
-                html.H4("Controls", className="card-title"),
-                html.Div("Upload meeting audio or video file:"),
-                dcc.Upload(
-                    id='audio-uploader',
-                    children=html.Div([
-                        'Drag and Drop or ',
-                        html.A('Select Audio/Video File')
-                    ]),
-                    style={
-                        'width': '100%',
-                        'height': '60px',
-                        'lineHeight': '60px',
-                        'borderWidth': '1px',
-                        'borderStyle': 'dashed',
-                        'borderRadius': '5px',
-                        'textAlign': 'center',
-                        'margin': '10px 0'
-                    },
-                    multiple=False,
-                    accept='audio/*,video/*'
-                ),
-                html.Div(id='upload-status', children='Status: Ready to Upload', className="mt-2"),
-                dbc.Button("Generate Minutes", id="minutes-btn", color="secondary", className="mt-3 w-100", disabled=True),
-                html.H5("Select AI Model", className="mt-4"),
-                dcc.Dropdown(
-                    id='model-selection',
-                    options=[
-                        {'label': 'OpenAI GPT-3.5 Turbo', 'value': 'openai', 'disabled': not openai.api_key},
-                        {'label': 'Google Gemini 1.5 Flash', 'value': 'gemini', 'disabled': not genai},
-                        {'label': 'Anthropic Claude 3.5 Haiku', 'value': 'anthropic', 'disabled': not anthropic},
-                        {'label': 'Grok 3 Mini', 'value': 'grok', 'disabled': not grok_api_key}
-                    ],
-                    value='openai' if openai.api_key else ('gemini' if genai else ('anthropic' if anthropic else ('grok' if grok_api_key else None))),
-                    clearable=False,
-                    className="mt-2",
-                    disabled=not (openai.api_key or genai or anthropic or grok_api_key)
-                ),
-                 dbc.Button("Delete Session Data", id="delete-btn", color="warning", className="mt-4 w-100", disabled=True),
-            ]),
-             style={'height': '80vh', 'overflow-y': 'auto'}
-        ), width=12, lg=4),
-        dbc.Col(dbc.Card(
-             dbc.CardBody([
-                dcc.Loading(
-                    id="loading",
-                    type="default",
-                    parent_style={'position': 'relative', 'height': '100%'},
-                    style={'position': 'absolute', 'top': '50%', 'left': '50%', 'transform': 'translate(-50%, -50%)', 'zIndex':'1000'},
-                    children=[
-                         html.Div([
-                            html.H4("Output", className="card-title"),
-                            html.Div(id="status", children="Status: Idle", className="mb-2"),
-                            html.H5("Transcript / Minutes"),
-                            html.Div(id="transcript-preview", style={
-                                "height": "400px",
-                                "overflow-y": "scroll",
-                                "border": "1px solid #ccc",
-                                "padding": "10px",
-                                "white-space": "pre-wrap",
-                                "word-wrap": "break-word",
-                                "background-color": "#f9f9f9"
-                            }),
-                            html.H5("Downloads", className="mt-3"),
-                             dbc.Row([
-                                dbc.Col(dbc.Button("Download Transcript (.docx)", id="download-transcript-btn", color="info", className="w-100 mb-2", disabled=True), width=12, md=4),
-                                dbc.Col(dbc.Button("Download Minutes (.docx)", id="download-minutes-btn", color="info", className="w-100 mb-2", disabled=True), width=12, md=4),
-                                dbc.Col(dbc.Button("Download Processed Audio", id="download-audio-btn", color="info", className="w-100 mb-2", disabled=True), width=12, md=4),
-                             ]),
-                         ])
-                    ]
-                 ),
-                 html.Div(id="loading-output", style={"height": "0px", "visibility": "hidden"}),
-            ]),
-            style={'height': '80vh', 'overflow-y': 'auto', 'position': 'relative'}
-        ), width=12, lg=8),
+        dbc.Col(
+            dbc.Card(
+                dbc.CardBody([
+                    html.H4("Controls", className="card-title"),
+                    html.Div("Upload meeting audio or video file:"),
+                    dcc.Upload(
+                        id='audio-uploader',
+                        children=html.Div([
+                            'Drag and Drop or ',
+                            html.A('Select Audio/Video File')
+                        ]),
+                        style={
+                            'width': '100%',
+                            'height': '60px',
+                            'lineHeight': '60px',
+                            'borderWidth': '1px',
+                            'borderStyle': 'dashed',
+                            'borderRadius': '5px',
+                            'textAlign': 'center',
+                            'margin': '10px 0'
+                        },
+                        multiple=False,
+                        accept='audio/*,video/*'
+                    ),
+                    html.Div(id='upload-status', children='Status: Ready to Upload', className="mt-2"),
+                    html.Div(id='uploaded-filename', style={'fontWeight': 'bold', 'marginBottom': '8px'}),
+                    html.Hr(),
+                    html.H5("View Output", className="mt-2"),
+                    dbc.Button("View Original Transcript", id="nav-original-btn", color="tertiary", className="mb-2 w-100"),
+                    dbc.Button("View Diarized Transcript", id="nav-diarized-btn", color="tertiary", className="mb-2 w-100"),
+                    dbc.Button("View Minutes", id="nav-minutes-btn", color="tertiary", className="mb-2 w-100"),
+                    html.Hr(),
+                    html.H5("Select AI Model", className="mt-2"),
+                    dcc.Dropdown(
+                        id='model-selection',
+                        options=[
+                            {'label': 'OpenAI GPT-3.5 Turbo', 'value': 'openai', 'disabled': not openai.api_key},
+                            {'label': 'Google Gemini 1.5 Flash', 'value': 'gemini', 'disabled': not genai},
+                            {'label': 'Anthropic Claude 3.5 Haiku', 'value': 'anthropic', 'disabled': not anthropic},
+                            {'label': 'Grok 3 Mini', 'value': 'grok', 'disabled': not grok_api_key}
+                        ],
+                        value='openai' if openai.api_key else (
+                            'gemini' if genai else (
+                                'anthropic' if anthropic else (
+                                    'grok' if grok_api_key else None
+                                )
+                            )
+                        ),
+                        clearable=False,
+                        className="mt-2",
+                        disabled=not (openai.api_key or genai or anthropic or grok_api_key)
+                    ),
+                    dbc.Checkbox(
+                        id="diarize-checkbox",
+                        className="mt-3",
+                        value=False,
+                        label="Diarize Speakers (AI)",
+                        style={"fontWeight": "bold"}
+                    ),
+                    dbc.Button("Diarize Transcript (Simple)", id="diarize-btn", color="primary", className="mt-2 w-100", disabled=True),
+                    dbc.Button("Diarize Transcript (Advanced)", id="advanced-diarize-btn", color="secondary", className="mt-2 w-100", disabled=True),
+                    dbc.Button("Download Diarized Transcript (.docx)", id="download-diarized-btn", color="info", className="mt-2 w-100", disabled=True),
+                    dbc.Button("Generate Minutes", id="minutes-btn", color="secondary", className="mt-4 w-100", disabled=True),
+                    dbc.Button("Delete Session Data", id="delete-btn", color="warning", className="mt-4 w-100", disabled=True),
+                ]),
+                style={'height': '80vh', 'overflow-y': 'auto'}
+            ), width=12, lg=4
+        ),
+        dbc.Col(
+            dbc.Card(
+                dbc.CardBody([
+                    dcc.Loading(
+                        id="loading",
+                        type="default",
+                        parent_style={'position': 'relative', 'height': '100%'},
+                        style={'position': 'absolute', 'top': '50%', 'left': '50%', 'transform': 'translate(-50%, -50%)', 'zIndex':'1000'},
+                        children=[
+                            html.Div([
+                                html.H4("Output", className="card-title"),
+                                html.Div(id="status", children="Status: Idle", className="mb-2"),
+                                html.H5("Transcript / Minutes"),
+                                html.Div(id="transcript-preview", style={
+                                    "height": "400px",
+                                    "overflow-y": "scroll",
+                                    "border": "1px solid #ccc",
+                                    "padding": "10px",
+                                    "white-space": "pre-wrap",
+                                    "word-wrap": "break-word",
+                                    "background-color": "#f9f9f9"
+                                }),
+                                html.H5("Downloads", className="mt-3"),
+                                dbc.Row([
+                                    dbc.Col(dbc.Button("Download Transcript (.docx)", id="download-transcript-btn", color="info", className="w-100 mb-2", disabled=True), width=12, md=4),
+                                    dbc.Col(dbc.Button("Download Minutes (.docx)", id="download-minutes-btn", color="info", className="w-100 mb-2", disabled=True), width=12, md=4),
+                                    dbc.Col(dbc.Button("Download Processed Audio", id="download-audio-btn", color="info", className="w-100 mb-2", disabled=True), width=12, md=4),
+                                ]),
+                            ])
+                        ]
+                    ),
+                    html.Div(id="loading-output", style={"height": "0px", "visibility": "hidden"}),
+                ]),
+                style={'height': '80vh', 'overflow-y': 'auto', 'position': 'relative'}
+            ), width=12, lg=8
+        ),
     ])
 ], fluid=True)
 
@@ -392,38 +607,81 @@ def manage_session_id(existing_session_id):
     return final_session_id
 
 @app.callback(
-    [Output("status", "children"),
-     Output("transcript-preview", "children"),
-     Output("minutes-btn", "disabled"),
-     Output("download-transcript-btn", "disabled"),
-     Output("download-minutes-btn", "disabled"),
-     Output("download-audio-btn", "disabled"),
-     Output("delete-btn", "disabled"),
-     Output("loading-output", "children"),
-     Output("upload-status", "children")],
-    [Input('audio-uploader', 'contents'),
-     Input("minutes-btn", "n_clicks"),
-     Input("delete-btn", "n_clicks")],
-    [State("session-id", "data"),
-     State("model-selection", "value"),
-     State("transcript-preview", "children"),
-     State('audio-uploader', 'filename')],
+    [
+        Output("status", "children"),
+        Output("transcript-preview", "children"),
+        Output("minutes-btn", "disabled"),
+        Output("download-transcript-btn", "disabled"),
+        Output("download-minutes-btn", "disabled"),
+        Output("download-audio-btn", "disabled"),
+        Output("delete-btn", "disabled"),
+        Output("loading-output", "children"),
+        Output("upload-status", "children"),
+        Output("diarize-btn", "disabled"),
+        Output("download-diarized-btn", "disabled"),
+        Output("uploaded-filename", "children"),
+        Output("advanced-diarize-btn", "disabled"),
+    ],
+    [
+        Input('audio-uploader', 'contents'),
+        Input("minutes-btn", "n_clicks"),
+        Input("delete-btn", "n_clicks"),
+        Input("diarize-btn", "n_clicks"),
+        Input("diarize-checkbox", "value"),
+        Input("nav-original-btn", "n_clicks"),
+        Input("nav-diarized-btn", "n_clicks"),
+        Input("nav-minutes-btn", "n_clicks"),
+        Input("advanced-diarize-btn", "n_clicks"),
+    ],
+    [
+        State("session-id", "data"),
+        State("model-selection", "value"),
+        State("transcript-preview", "children"),
+        State('audio-uploader', 'filename'),
+        State("diarize-checkbox", "value")
+    ],
     prevent_initial_call=True
 )
-def handle_actions(upload_contents, minutes_clicks, delete_clicks, session_id, selected_model, existing_preview, filename):
+def handle_actions(
+    upload_contents, minutes_clicks, delete_clicks, diarize_clicks, diarize_checkbox_val,
+    nav_original_clicks, nav_diarized_clicks, nav_minutes_clicks, advanced_diarize_clicks,
+    session_id, selected_model, existing_preview, filename, diarize_checkbox_val2
+):
+    diarize_checkbox = diarize_checkbox_val if diarize_checkbox_val is not None else diarize_checkbox_val2
     if not session_id:
         logging.warning("Session ID missing in handle_actions.")
-        return "Status: Error - Session ID missing", "", True, True, True, True, True, None, "Status: Error"
+        return "Status: Error - Session ID missing", "", True, True, True, True, True, None, "Status: Error", True, True, "", True
     ctx = dash.callback_context
     triggered_id = ctx.triggered_id if hasattr(ctx, 'triggered_id') else (ctx.triggered[0]['prop_id'].split('.')[0] if ctx.triggered else None)
     current_transcript = session_data[session_id].get("transcript", "")
     current_minutes = session_data[session_id].get("minutes", "")
     current_audio_path = session_data[session_id].get("audio_path", None)
     original_filename = session_data[session_id].get("original_filename", None)
-    output_text = current_minutes if current_minutes else (current_transcript if current_transcript else "Upload an audio or video file to begin.")
+    diarized_transcript = session_data[session_id].get("diarized_transcript", None)
+    diarization_done = session_data[session_id].get("diarization_done", False)
+    advanced_diarized_transcript = session_data[session_id].get("advanced_diarized_transcript", None)
+    preview_mode = session_data[session_id].get("preview_mode", "auto")
+    output_text = ""
+    # Preview mode logic
+    if preview_mode == "original":
+        output_text = current_transcript if current_transcript else "No transcript available."
+    elif preview_mode == "diarized":
+        output_text = advanced_diarized_transcript if advanced_diarized_transcript else (diarized_transcript if diarized_transcript else "No diarized transcript available.")
+    elif preview_mode == "minutes":
+        output_text = current_minutes if current_minutes else "No minutes available."
+    else:
+        output_text = current_minutes if current_minutes else (
+            advanced_diarized_transcript if advanced_diarized_transcript else (
+                diarized_transcript if diarize_checkbox and diarized_transcript else (
+                    current_transcript if current_transcript else "Upload an audio or video file to begin."
+                )
+            )
+        )
     status_msg = "Status: Idle"
     if current_minutes and "Error:" not in current_minutes:
         status_msg = "Status: Session restored. Minutes loaded."
+    elif (diarize_checkbox or advanced_diarized_transcript) and (advanced_diarized_transcript or diarized_transcript) and "Error:" not in (advanced_diarized_transcript or diarized_transcript or ""):
+        status_msg = "Status: Session restored. Diarized transcript loaded."
     elif current_transcript and "Error:" not in current_transcript:
         status_msg = "Status: Session restored. Transcript loaded. Ready for Minutes Generation."
     elif current_audio_path and os.path.exists(current_audio_path):
@@ -435,12 +693,18 @@ def handle_actions(upload_contents, minutes_clicks, delete_clicks, session_id, s
     dl_minutes_disabled = not bool(current_minutes and "Error:" not in current_minutes)
     dl_audio_disabled = not bool(current_audio_path and os.path.exists(current_audio_path))
     delete_disabled = not bool(session_data.get(session_id, {}).get("temp_dir"))
+    diarize_disabled = not bool(current_transcript and "Error:" not in current_transcript)
+    dl_diarized_disabled = not bool((advanced_diarized_transcript or diarized_transcript) and "Error:" not in (advanced_diarized_transcript or diarized_transcript or ""))
+    uploaded_filename_text = original_filename if original_filename else ""
+    advanced_diarize_disabled = diarize_disabled
     loading_output = None
     upload_status_msg = f"Status: {'Loaded: ' + original_filename if original_filename else 'Ready to Upload'}"
     start_time = time.time()
+    # File upload logic
     if triggered_id == 'audio-uploader' and upload_contents is not None and filename is not None:
         logging.info(f"File uploaded for session {session_id}, filename: {filename}")
         session_data[session_id]["original_filename"] = filename
+        uploaded_filename_text = filename
         upload_status_msg = f"Status: Processing Uploaded File ({filename})..."
         status_msg = "Status: Processing Upload..."
         loading_output = "Processing Upload..."
@@ -455,12 +719,18 @@ def handle_actions(upload_contents, minutes_clicks, delete_clicks, session_id, s
              session_data[session_id]["transcript"] = None
              session_data[session_id]["minutes"] = None
              session_data[session_id]["original_filename"] = None
+             session_data[session_id]["diarized_transcript"] = None
+             session_data[session_id]["diarization_done"] = False
+             session_data[session_id]["advanced_diarized_transcript"] = None
              minutes_disabled = True
              dl_transcript_disabled = True
              dl_minutes_disabled = True
              dl_audio_disabled = True
              delete_disabled = False
-             return status_msg, output_text, minutes_disabled, dl_transcript_disabled, dl_minutes_disabled, dl_audio_disabled, delete_disabled, None, upload_status_msg
+             diarize_disabled = True
+             dl_diarized_disabled = True
+             advanced_diarize_disabled = True
+             return status_msg, output_text, minutes_disabled, dl_transcript_disabled, dl_minutes_disabled, dl_audio_disabled, delete_disabled, None, upload_status_msg, diarize_disabled, dl_diarized_disabled, uploaded_filename_text, advanced_diarize_disabled
         safe_upload_filename = f"uploaded_file{f_ext}"
         upload_file_path = os.path.join(session_dir, safe_upload_filename)
         saved_upload_path = save_base64_data(upload_contents, upload_file_path)
@@ -492,7 +762,13 @@ def handle_actions(upload_contents, minutes_clicks, delete_clicks, session_id, s
                     dl_minutes_disabled = True
                     dl_audio_disabled = True
                     delete_disabled = False
-                    return status_msg, output_text, minutes_disabled, dl_transcript_disabled, dl_minutes_disabled, dl_audio_disabled, delete_disabled, None, upload_status_msg
+                    diarize_disabled = True
+                    dl_diarized_disabled = True
+                    session_data[session_id]["diarized_transcript"] = None
+                    session_data[session_id]["diarization_done"] = False
+                    session_data[session_id]["advanced_diarized_transcript"] = None
+                    advanced_diarize_disabled = True
+                    return status_msg, output_text, minutes_disabled, dl_transcript_disabled, dl_minutes_disabled, dl_audio_disabled, delete_disabled, None, upload_status_msg, diarize_disabled, dl_diarized_disabled, uploaded_filename_text, advanced_diarize_disabled
             else:
                 audio_path_for_transcription = saved_upload_path
                 session_data[session_id]["audio_path"] = saved_upload_path
@@ -505,6 +781,9 @@ def handle_actions(upload_contents, minutes_clicks, delete_clicks, session_id, s
                 transcript_text = transcribe_audio(audio_path_for_transcription)
                 session_data[session_id]["transcript"] = transcript_text
                 session_data[session_id]["minutes"] = None
+                session_data[session_id]["diarized_transcript"] = None
+                session_data[session_id]["diarization_done"] = False
+                session_data[session_id]["advanced_diarized_transcript"] = None
                 if "Error:" in transcript_text:
                      status_msg = f"Status: Transcription Failed - {transcript_text}"
                      output_text = transcript_text
@@ -513,6 +792,9 @@ def handle_actions(upload_contents, minutes_clicks, delete_clicks, session_id, s
                      dl_minutes_disabled = True
                      delete_disabled = False
                      upload_status_msg = f"Status: Transcription Failed. ({filename})"
+                     diarize_disabled = True
+                     dl_diarized_disabled = True
+                     advanced_diarize_disabled = True
                 else:
                      status_msg = "Status: Transcription Complete. Ready for Minutes Generation."
                      output_text = transcript_text
@@ -521,6 +803,9 @@ def handle_actions(upload_contents, minutes_clicks, delete_clicks, session_id, s
                      dl_minutes_disabled = True
                      delete_disabled = False
                      upload_status_msg = f"Status: Processed & Transcribed: {filename}"
+                     diarize_disabled = False
+                     dl_diarized_disabled = True
+                     advanced_diarize_disabled = False
                 processing_time = time.time() - start_time
                 logging.info(f"File processing and transcription took {processing_time:.2f} seconds for session {session_id}")
         else:
@@ -534,15 +819,28 @@ def handle_actions(upload_contents, minutes_clicks, delete_clicks, session_id, s
             dl_minutes_disabled = True
             dl_audio_disabled = True
             delete_disabled = False
+            diarize_disabled = True
+            dl_diarized_disabled = True
+            session_data[session_id]["diarized_transcript"] = None
+            session_data[session_id]["diarization_done"] = False
+            session_data[session_id]["advanced_diarized_transcript"] = None
+            advanced_diarize_disabled = True
     elif triggered_id == "minutes-btn" and minutes_clicks:
         logging.info(f"Generate Minutes button clicked for session {session_id}")
-        current_transcript = session_data[session_id].get("transcript", "")
-        if current_transcript and "Error:" not in current_transcript:
+        transcript_to_use = None
+        if preview_mode == "diarized":
+            transcript_to_use = advanced_diarized_transcript if advanced_diarized_transcript else diarized_transcript
+        elif diarize_checkbox and (advanced_diarized_transcript or diarized_transcript):
+            transcript_to_use = advanced_diarized_transcript if advanced_diarized_transcript else diarized_transcript
+        else:
+            transcript_to_use = current_transcript
+        if transcript_to_use and "Error:" not in transcript_to_use:
             status_msg = f"Status: Generating Minutes ({selected_model})..."
             loading_output = "Generating Minutes..."
-            minutes_text = generate_minutes_ai(current_transcript, selected_model, session_id)
+            minutes_text = generate_minutes_ai(transcript_to_use, selected_model, session_id)
             session_data[session_id]["minutes"] = minutes_text
             output_text = minutes_text
+            session_data[session_id]["preview_mode"] = "minutes"
             if "Error:" in minutes_text:
                 status_msg = f"Status: Minutes Generation Failed - {minutes_text}"
                 dl_minutes_disabled = True
@@ -556,10 +854,77 @@ def handle_actions(upload_contents, minutes_clicks, delete_clicks, session_id, s
             dl_audio_disabled = not bool(session_data.get(session_id, {}).get("audio_path") and os.path.exists(session_data.get(session_id, {}).get("audio_path", "")))
             delete_disabled = False
             upload_status_msg = f"Status: Processed & Transcribed: {session_data[session_id].get('original_filename', 'File')}"
+            diarize_disabled = not bool(session_data[session_id].get("transcript") and "Error:" not in session_data[session_id].get("transcript"))
+            dl_diarized_disabled = not bool((session_data[session_id].get("advanced_diarized_transcript") or session_data[session_id].get("diarized_transcript")) and "Error:" not in (session_data[session_id].get("advanced_diarized_transcript") or session_data[session_id].get("diarized_transcript") or ""))
+            advanced_diarize_disabled = diarize_disabled
         else:
             status_msg = "Status: Cannot generate minutes - No valid transcript available."
             output_text = existing_preview
             minutes_disabled = True
+    elif triggered_id == "diarize-btn" and diarize_clicks:
+        logging.info(f"Diarize button clicked for session {session_id}")
+        current_transcript = session_data[session_id].get("transcript", "")
+        if current_transcript and "Error:" not in current_transcript:
+            status_msg = f"Status: Diarizing Transcript ({selected_model})..."
+            loading_output = "Diarizing..."
+            diarized_text = diarize_transcript_ai(current_transcript, selected_model, session_id)
+            session_data[session_id]["diarized_transcript"] = diarized_text
+            session_data[session_id]["diarization_done"] = "Error:" not in diarized_text
+            output_text = diarized_text
+            session_data[session_id]["preview_mode"] = "diarized"
+            if "Error:" in diarized_text:
+                status_msg = f"Status: Diarization Failed - {diarized_text}"
+                dl_diarized_disabled = True
+            else:
+                status_msg = "Status: Diarization Complete."
+                dl_diarized_disabled = False
+            diarize_disabled = False
+            advanced_diarize_disabled = False
+        else:
+            status_msg = "Status: Cannot diarize - No valid transcript available."
+            output_text = existing_preview
+            diarize_disabled = True
+            dl_diarized_disabled = True
+            advanced_diarize_disabled = True
+    elif triggered_id == "advanced-diarize-btn" and advanced_diarize_clicks:
+        logging.info(f"Advanced Diarize button clicked for session {session_id}")
+        current_transcript = session_data[session_id].get("transcript", "")
+        if current_transcript and "Error:" not in current_transcript:
+            status_msg = f"Status: Advanced Diarizing Transcript ({selected_model})..."
+            loading_output = "Advanced Diarizing..."
+            adv_diarized_text = advanced_diarize_transcript_ai(current_transcript, selected_model, session_id)
+            session_data[session_id]["advanced_diarized_transcript"] = adv_diarized_text
+            output_text = adv_diarized_text
+            session_data[session_id]["preview_mode"] = "diarized"
+            if "Error:" in adv_diarized_text:
+                status_msg = f"Status: Advanced Diarization Failed - {adv_diarized_text}"
+                dl_diarized_disabled = True
+            else:
+                status_msg = "Status: Advanced Diarization Complete."
+                dl_diarized_disabled = False
+            diarize_disabled = False
+            advanced_diarize_disabled = False
+        else:
+            status_msg = "Status: Cannot advanced diarize - No valid transcript available."
+            output_text = existing_preview
+            diarize_disabled = True
+            dl_diarized_disabled = True
+            advanced_diarize_disabled = True
+    elif triggered_id == "nav-original-btn" and nav_original_clicks:
+        logging.info(f"Nav: View Original Transcript for session {session_id}")
+        output_text = current_transcript if current_transcript else "No transcript available."
+        session_data[session_id]["preview_mode"] = "original"
+        status_msg = "Status: Viewing Original Transcript."
+    elif triggered_id == "nav-diarized-btn" and nav_diarized_clicks:
+        logging.info(f"Nav: View Diarized Transcript for session {session_id}")
+        output_text = advanced_diarized_transcript if advanced_diarized_transcript else (diarized_transcript if diarized_transcript else "No diarized transcript available.")
+        session_data[session_id]["preview_mode"] = "diarized"
+        status_msg = "Status: Viewing Diarized Transcript."
+    elif triggered_id == "nav-minutes-btn" and nav_minutes_clicks:
+        logging.info(f"Nav: View Minutes for session {session_id}")
+        output_text = current_minutes if current_minutes else "No minutes available."
+        session_data[session_id]["preview_mode"] = "minutes"
+        status_msg = "Status: Viewing Minutes."
     elif triggered_id == "delete-btn" and delete_clicks:
         logging.info(f"Delete button clicked for session {session_id}")
         cleanup_session(session_id)
@@ -570,24 +935,49 @@ def handle_actions(upload_contents, minutes_clicks, delete_clicks, session_id, s
         dl_minutes_disabled = True
         dl_audio_disabled = True
         delete_disabled = True
+        diarize_disabled = True
+        dl_diarized_disabled = True
+        advanced_diarize_disabled = True
         upload_status_msg = "Status: Ready to Upload"
+        uploaded_filename_text = ""
     else:
-         loaded_audio_path = session_data.get(session_id, {}).get("audio_path")
-         loaded_transcript = session_data.get(session_id, {}).get("transcript")
-         loaded_minutes = session_data.get(session_id, {}).get("minutes")
-         temp_dir_exists = bool(session_data.get(session_id, {}).get("temp_dir"))
-         loaded_original_filename = session_data.get(session_id, {}).get("original_filename")
-         dl_audio_disabled = not (loaded_audio_path and os.path.exists(loaded_audio_path))
-         minutes_disabled = not (loaded_transcript and "Error:" not in loaded_transcript)
-         dl_transcript_disabled = not (loaded_transcript and "Error:" not in loaded_transcript)
-         dl_minutes_disabled = not (loaded_minutes and "Error:" not in loaded_minutes)
-         delete_disabled = not (loaded_audio_path or loaded_transcript or loaded_minutes or temp_dir_exists or loaded_original_filename)
-         if loaded_original_filename and dl_audio_disabled and not loaded_transcript:
-             upload_status_msg = f"Status: Error processing {loaded_original_filename}?"
-         elif loaded_audio_path and os.path.exists(loaded_audio_path):
-             upload_status_msg = f"Status: Processed audio loaded ({loaded_original_filename or 'previous file'})."
-         else:
-             upload_status_msg = "Status: Ready to Upload"
+        loaded_audio_path = session_data.get(session_id, {}).get("audio_path")
+        loaded_transcript = session_data.get(session_id, {}).get("transcript")
+        loaded_minutes = session_data.get(session_id, {}).get("minutes")
+        loaded_diarized = session_data.get(session_id, {}).get("diarized_transcript")
+        loaded_adv_diarized = session_data.get(session_id, {}).get("advanced_diarized_transcript")
+        temp_dir_exists = bool(session_data.get(session_id, {}).get("temp_dir"))
+        loaded_original_filename = session_data.get(session_id, {}).get("original_filename")
+        dl_audio_disabled = not (loaded_audio_path and os.path.exists(loaded_audio_path))
+        minutes_disabled = not (loaded_transcript and "Error:" not in loaded_transcript)
+        dl_transcript_disabled = not (loaded_transcript and "Error:" not in loaded_transcript)
+        dl_minutes_disabled = not (loaded_minutes and "Error:" not in loaded_minutes)
+        diarize_disabled = not (loaded_transcript and "Error:" not in loaded_transcript)
+        advanced_diarize_disabled = diarize_disabled
+        dl_diarized_disabled = not ((loaded_adv_diarized or loaded_diarized) and "Error:" not in (loaded_adv_diarized or loaded_diarized or ""))
+        delete_disabled = not (loaded_audio_path or loaded_transcript or loaded_minutes or loaded_diarized or temp_dir_exists or loaded_original_filename or loaded_adv_diarized)
+        if loaded_original_filename and dl_audio_disabled and not loaded_transcript:
+            upload_status_msg = f"Status: Error processing {loaded_original_filename}?"
+        elif loaded_audio_path and os.path.exists(loaded_audio_path):
+            upload_status_msg = f"Status: Processed audio loaded ({loaded_original_filename or 'previous file'})."
+        else:
+            upload_status_msg = "Status: Ready to Upload"
+        uploaded_filename_text = loaded_original_filename if loaded_original_filename else ""
+        pmode = session_data[session_id].get("preview_mode", "auto")
+        if pmode == "original":
+            output_text = loaded_transcript if loaded_transcript else "No transcript available."
+        elif pmode == "diarized":
+            output_text = loaded_adv_diarized if loaded_adv_diarized else (loaded_diarized if loaded_diarized else "No diarized transcript available.")
+        elif pmode == "minutes":
+            output_text = loaded_minutes if loaded_minutes else "No minutes available."
+        else:
+            output_text = loaded_minutes if loaded_minutes else (
+                loaded_adv_diarized if loaded_adv_diarized else (
+                    loaded_diarized if diarize_checkbox and loaded_diarized else (
+                        loaded_transcript if loaded_transcript else "Upload an audio or video file to begin."
+                    )
+                )
+            )
     return (
         status_msg,
         output_text,
@@ -597,7 +987,11 @@ def handle_actions(upload_contents, minutes_clicks, delete_clicks, session_id, s
         dl_audio_disabled,
         delete_disabled,
         loading_output,
-        upload_status_msg
+        upload_status_msg,
+        diarize_disabled,
+        dl_diarized_disabled,
+        uploaded_filename_text,
+        advanced_diarize_disabled
     )
 
 @app.callback(
@@ -674,7 +1068,37 @@ def download_audio_file(n_clicks, session_id):
         logging.error(f"Processed audio file not found at path {audio_path} for session {session_id}")
         return None
 
+@app.callback(
+    Output("download-diarized", "data"),
+    Input("download-diarized-btn", "n_clicks"),
+    State("session-id", "data"),
+    prevent_initial_call=True,
+)
+def download_diarized_file(n_clicks, session_id):
+    diarized = None
+    if session_id and session_data.get(session_id, {}).get("advanced_diarized_transcript"):
+        diarized = session_data[session_id]["advanced_diarized_transcript"]
+    elif session_id and session_data.get(session_id, {}).get("diarized_transcript"):
+        diarized = session_data[session_id]["diarized_transcript"]
+    else:
+        logging.warning(f"Download diarized transcript requested but no data found for session {session_id}.")
+        return None
+    if "Error:" in diarized:
+        logging.warning(f"Attempted to download diarized transcript containing an error for session {session_id}.")
+        return None
+    session_dir = get_session_dir(session_id)
+    diarized_filename = os.path.join(session_dir, f"diarized_{uuid.uuid4()}.docx")
+    saved_doc_path = save_to_word(diarized, diarized_filename)
+    if saved_doc_path:
+         logging.info(f"Sending diarized transcript file: {saved_doc_path}")
+         original_filename_base = os.path.splitext(session_data[session_id].get("original_filename", "meeting"))[0]
+         download_filename = f"{original_filename_base}_diarized.docx"
+         return dcc.send_file(saved_doc_path, filename=download_filename)
+    else:
+         logging.error(f"Failed to create Word document for diarized transcript download for session {session_id}")
+         return dcc.send_data_frame(lambda: diarized, "meeting_diarized.txt")
+
 if __name__ == '__main__':
     print("Starting the Dash application...")
-    app.run(debug=False, host='0.0.0.0', port=7860)
+    app.run(debug=True, host='0.0.0.0', port=7860)
     print("Dash application has finished running.")