Create app.py

app.py

@@ -0,0 +1,49 @@
+import gradio as gr
+from transformers import pipeline
+import pyttsx3
+
+# Load pipelines
+sentiment_model = pipeline("sentiment-analysis")
+summarizer_model = pipeline("summarization")
+# Text-to-Speech using pyttsx3 (offline TTS engine)
+engine = pyttsx3.init()
+
+# Define Sentiment Analysis function
+def analyze_sentiment(text):
+    result = sentiment_model(text)[0]
+    return f"Sentiment: {result['label']}, Confidence: {result['score']:.2f}"
+
+# Define Summarization function
+def summarize_text(text):
+    summary = summarizer_model(text, max_length=60, min_length=15, do_sample=False)
+    return summary[0]['summary_text']
+
+# Define TTS function and save to file
+def text_to_speech(text):
+    filename = "output_audio.wav"
+    engine.save_to_file(text, filename)
+    engine.runAndWait()
+    return filename
+
+# Create Gradio interface
+with gr.Blocks() as demo:
+    gr.Markdown("## 🧠 NLP Tools: Sentiment | Summarization | Text-to-Speech")
+    
+    with gr.Row():
+        input_text = gr.Textbox(label="Enter your text here", lines=6, placeholder="Type or paste your text here...")
+
+    with gr.Row():
+        sentiment_btn = gr.Button("🔍 Analyze Sentiment")
+        summarize_btn = gr.Button("📝 Summarize")
+        tts_btn = gr.Button("🔊 Text to Speech")
+
+    with gr.Row():
+        sentiment_output = gr.Textbox(label="Sentiment Result")
+        summary_output = gr.Textbox(label="Summary")
+        audio_output = gr.Audio(label="Audio Output")
+
+    sentiment_btn.click(analyze_sentiment, inputs=input_text, outputs=sentiment_output)
+    summarize_btn.click(summarize_text, inputs=input_text, outputs=summary_output)
+    tts_btn.click(text_to_speech, inputs=input_text, outputs=audio_output)
+
+demo.launch()