Merge pull request #159 from Fosowl/dev

Fixed tts not working with web interface

api.py

@@ -151,9 +151,8 @@ async def get_latest_answer():
         return JSONResponse(status_code=200, content=query_resp_history[-1])
     return JSONResponse(status_code=404, content={"error": "No answer available"})
 
-async def think_wrapper(interaction, query, tts_enabled):
+async def think_wrapper(interaction, query):
     try:
-        interaction.tts_enabled = tts_enabled
         interaction.last_query = query
         logger.info("Agents request is being processed")
         success = await interaction.think()
@@ -162,6 +161,8 @@ async def think_wrapper(interaction, query, tts_enabled):
             interaction.last_success = False
         else:
             interaction.last_success = True
+        pretty_print(interaction.last_answer)
+        interaction.speak_answer()
         return success
     except Exception as e:
         logger.error(f"Error in think_wrapper: {str(e)}")
@@ -188,7 +189,7 @@ async def process_query(request: QueryRequest):
 
     try:
         is_generating = True
-        success = await think_wrapper(interaction, request.query, request.tts_enabled)
+        success = await think_wrapper(interaction, request.query)
         is_generating = False
 
         if not success:

cli.py

@@ -62,6 +62,7 @@ async def main():
             interaction.get_user()
             if await interaction.think():
                 interaction.show_answer()
+                interaction.speak_answer()
     except Exception as e:
         if config.getboolean('MAIN', 'save_session'):
             interaction.save_session()

sources/agents/browser_agent.py

@@ -250,6 +250,7 @@ class BrowserAgent(Agent):
 
         Expand on the finding or step that lead to success, and provide a conclusion that answer the request. Include link when possible.
         Do not give advices or try to answer the human. Just structure the AI finding in a structured and clear way.
+        You should answer in the same language as the user.
         """
     
     def search_prompt(self, user_prompt: str) -> str:

sources/interaction.py

@@ -5,6 +5,7 @@ from sources.text_to_speech import Speech
 from sources.utility import pretty_print, animate_thinking
 from sources.router import AgentRouter
 from sources.speech_to_text import AudioTranscriber, AudioRecorder
+import threading
 
 
 class Interaction:
@@ -173,12 +174,20 @@ class Interaction:
             return None
         return self.current_agent.get_last_block_answer()
     
+    def speak_answer(self) -> None:
+        """Speak the answer to the user in a non-blocking thread."""
+        if self.last_query is None:
+            return
+        if self.tts_enabled and self.last_answer and self.speech:
+            def speak_in_thread(speech_instance, text):
+                speech_instance.speak(text)
+            thread = threading.Thread(target=speak_in_thread, args=(self.speech, self.last_answer))
+            thread.start()
+    
     def show_answer(self) -> None:
         """Show the answer to the user."""
         if self.last_query is None:
             return
         if self.current_agent is not None:
             self.current_agent.show_answer()
-        if self.tts_enabled and self.last_answer:
-            self.speech.speak(self.last_answer)
 

sources/text_to_speech.py

@@ -173,10 +173,10 @@ if __name__ == "__main__":
     tosay_fr = """
     J'ai consulté les dernières nouvelles sur le site https://www.theguardian.com/world
     """
-    spk = Speech(enable=True, language="ja", voice_idx=2)
+    spk = Speech(enable=True, language="zh", voice_idx=0)
     for i in range(0, 2):
         print(f"Speaking chinese with voice {i}")
-        spk.speak(tosay_ja, voice_idx=i)
+        spk.speak(tosay_zh, voice_idx=i)
     spk = Speech(enable=True, language="en", voice_idx=2)
     for i in range(0, 5):
         print(f"Speaking english with voice {i}")