TTS

Author: NEJANX

templates/index.html

@@ -997,16 +997,52 @@ <h1>Yuhasa History Tutor</h1>
                 alert('Attachment functionality is not yet implemented.');
             });
 
-            speakerButton.addEventListener('click', () => {
-                alert('Text-to-speech functionality is not yet implemented.');
-            });
+            // speakerButton.addEventListener('click', () => {
+            //     alert('Text-to-speech functionality is not yet implemented.');
+            // });
 
             // --- Initial Setup ---
             loadChatHistoryList(true); // Load the list of chats and select latest on page load
             userInput.focus();
             autoResizeTextarea();
         });
     </script>
+
+<script>
+    document.getElementById('speakerButton').addEventListener('click', async function() {
+        // Find all bot messages in the chat
+        const botMessages = Array.from(document.querySelectorAll('.bot-message .message-bubble'));
+        if (botMessages.length === 0) {
+            alert('No bot message to speak!');
+            return;
+        }
+        // Get the last bot message's text
+        const lastBotMsg = botMessages[botMessages.length - 1].innerText.trim();
+        if (!lastBotMsg) {
+            alert('Bot message is empty!');
+            return;
+        }
+        try {
+            // Send the text to the /tts endpoint
+            const response = await fetch('/tts', {
+                method: 'POST',
+                headers: { 'Content-Type': 'application/json' },
+                body: JSON.stringify({ text: lastBotMsg })
+            });
+            if (!response.ok) {
+                throw new Error('TTS failed');
+            }
+            const blob = await response.blob();
+            // Play the audio using an Audio element
+            const audioUrl = URL.createObjectURL(blob);
+            const audio = new Audio(audioUrl);
+            audio.play();
+        } catch (err) {
+            alert('Failed to speak: ' + err.message);
+        }
+    });
+    </script>
+    
 </body>
 
 </html>

web.py

@@ -6,6 +6,9 @@
 import time
 from agents.orchestrator import OrchestratorAgent
 import traceback
+from gtts import gTTS
+from flask import send_file
+import io
 
 # --- Logging Setup ---
 logging.basicConfig(level=logging.INFO,
@@ -174,6 +177,24 @@ def api_delete_chat(chat_id):
     os.remove(path)
     return jsonify({'success': True})
 
+@app.route('/tts', methods=['POST'])
+def text_to_speech():
+    data = request.get_json()
+    text = data.get('text', '')
+    if not text:
+        return jsonify({'error': 'No text provided'}), 400
+    try:
+        # Generate speech using gTTS
+        tts = gTTS(text=text, lang='en')
+        mp3_fp = io.BytesIO()
+        tts.write_to_fp(mp3_fp)
+        mp3_fp.seek(0)
+        # Return the audio file as response
+        return send_file(mp3_fp, mimetype='audio/mpeg', as_attachment=False, download_name='speech.mp3')
+    except Exception as e:
+        logger.error(f"Error generating speech: {e}", exc_info=True)
+        return jsonify({'error': 'Failed to generate speech'}), 500
+
 if __name__ == '__main__':
     if orchestrator:
         logger.info("Starting Flask development server...")