Update app.py

app.py

@@ -1,64 +1,51 @@
-from smolagents import CodeAgent,DuckDuckGoSearchTool, HfApiModel,load_tool,tool
-import datetime
+import os
 import requests
-import pytz
+import random
 import yaml
+import datetime
+import pytz
+import gradio as gr
+from gtts import gTTS  # Use Google TTS instead of pyttsx3
+from smolagents import CodeAgent, DuckDuckGoSearchTool, HfApiModel, load_tool, tool
 from tools.final_answer import FinalAnswerTool
-from tools.web_search import DuckDuckGoSearchTool
-from tools.visit_webpage import VisitWebpageTool
-
 from Gradio_UI import GradioUI
 
-from kokoro import KPipeline
-import soundfile as sf
-import os
-import numpy as np
+# Define the audio output path
+AUDIO_OUTPUT_PATH = "/tmp/response.mp3"
 
-import gradio as gr
+def speak_text(text):
+    """Convert text to speech using gTTS and save as an MP3 file."""
+    tts = gTTS(text=text, lang='en')
+    tts.save(AUDIO_OUTPUT_PATH)
+    return AUDIO_OUTPUT_PATH  # Return the file path for Gradio Audio component
 
 
-# Initialize the Kokoro pipeline
-pipeline = KPipeline(lang_code='a')  # 'a' stands for American English
 
 @tool
-def text_to_speech_kokoro(text: str, voice: str = 'af_heart', speed: float = 1.0) -> str:
-    """
-    Convert text to speech using the Kokoro-82M model.
-
-    Parameters:
-        text (str): 
-            The text to be converted to speech.
-        voice (str, optional): 
-            The voice to use for speech synthesis. Defaults to 'af_heart'.
-        speed (float, optional): 
-            The speed of the speech. Defaults to 1.0.
-
-    Returns:
-        str: The path to the generated audio file.
+def search_dad_jokes(term: str) -> str:
+    """A tool that searches for dad jokes containing a specific term.
+    Args:
+        term: The keyword to search for in dad jokes.
     """
     try:
-        # Generate speech audio
-        generator = pipeline(text, voice=voice, speed=speed, split_pattern=r'\n+')
-        audio_segments = []
-        for _, _, audio in generator:
-            audio_segments.append(audio)
-        
-        if not audio_segments:
-            raise ValueError("No audio generated.")
-        
-        # Concatenate segments into one audio array
-        full_audio = np.concatenate(audio_segments)
-        sample_rate = 24000  # Kokoro outputs at 24 kHz
-
-        # Ensure the tools folder exists and save the file there
-        os.makedirs("tools", exist_ok=True)
-        filename = os.path.join("tools", "output.wav")
-        sf.write(filename, full_audio, sample_rate)
-
-        return filename  # Return the file path
+        headers = {
+            "Accept": "application/json",
+            "User-Agent": "YourAppName (https://yourappurl.com)"
+        }
+        response = requests.get(f"https://icanhazdadjoke.com/search?term={term}", headers=headers)
+        data = response.json()
+        if data['results']:
+            jokes = [joke['joke'] for joke in data['results']]
+            response_text = f"Found {len(jokes)} jokes:\n" + "\n\n".join(jokes)
+        else:
+            response_text = f"No jokes found for the term '{term}'."
     except Exception as e:
-        return f"Error generating speech: {str(e)}"
+        response_text = f"Error searching for jokes: {str(e)}"
+
+    # Generate audio using gTTS
+    audio_file = speak_text(response_text)
 
+    return response_text, audio_file  # Return text and audio file path
 
 
 final_answer = FinalAnswerTool()
@@ -96,7 +83,26 @@ agent = CodeAgent(
     prompt_templates=prompt_templates
 )
 
+# Gradio interface with text and audio output
+def gradio_define_word(word):
+    """Wrapper function for Gradio to call the define_word tool."""
+    response_text, audio_file = define_word(word)
+    return response_text, audio_file
+
+# Define the Gradio UI
+with gr.Blocks() as demo:
+    gr.Markdown("### Dictionary Lookup with AI & Text-to-Speech 🎙️")
+    with gr.Row():
+        input_box = gr.Textbox(label="Enter a word")
+        output_text = gr.Textbox(label="Definition")
+        output_audio = gr.Audio(label="Audio Pronunciation", type="filepath")
+    
+    btn = gr.Button("Get Definition")
+    btn.click(gradio_define_word, inputs=input_box, outputs=[output_text, output_audio])
+
+demo.launch()
+
 
-GradioUI(agent).launch()
+#GradioUI(agent).launch()