Update app.py

app.py

@@ -29,7 +29,7 @@ LANG_UI_TO_CODE = {"English": "en", "Spanish": "es", "French": "fr"}
 
 def translate_text(user_text, target_lang_ui):
     if not user_text.strip():
-        return "⚠️ Please enter text."
+        return ""
     target_code = LANG_UI_TO_CODE.get(target_lang_ui, "en")
     try:
         src_code = detect(user_text)
@@ -50,22 +50,19 @@ API_URL = "https://api.groq.ai/v1/text/analyze"
 
 def detect_emotion_tone(text):
     if not text.strip():
-        return "⚠ No text.", None
+        return "neutral"
     headers = {"Authorization": f"Bearer {GROQ_API_KEY}", "Content-Type": "application/json"}
-    payload = {"text": text, "features": ["emotion", "tone"]}
+    payload = {"text": text, "features": ["emotion"]}
     try:
         r = requests.post(API_URL, headers=headers, json=payload)
         r.raise_for_status()
         result = r.json()
         emotions = result.get("emotion", {})
-        tones = result.get("tone", {})
         if not emotions:
-            return "neutral", "neutral"
-        dominant_emotion = max(emotions, key=emotions.get)
-        dominant_tone = max(tones, key=tones.get) if tones else "neutral"
-        return dominant_emotion, dominant_tone
+            return "neutral"
+        return max(emotions, key=emotions.get)
     except Exception:
-        return "neutral", "neutral"
+        return "neutral"
 
 # ----------------------------
 # 4. TEXT TO SPEECH (Edge TTS)
@@ -89,17 +86,16 @@ async def full_pipeline(audio, target_lang):
     # Step 1: STT
     text = transcribe(audio)
     if not text:
-        return "⚠ No speech detected", "", "", None
+        return None
 
     # Step 2: Translate
     translated = translate_text(text, target_lang)
 
     # Step 3: Emotion Detection
-    emotion, tone = detect_emotion_tone(text)
+    emotion = detect_emotion_tone(text)
 
-    # Step 4: TTS (apply emotion by picking voice tone)
+    # Step 4: Pick voice based on emotion
     voices = await edge_tts.list_voices()
-    # Simple emotion → voice mapping
     if emotion == "happy":
         voice_choice = [v for v in voices if "en-US-AriaNeural" in v["ShortName"]]
     elif emotion == "sad":
@@ -110,30 +106,24 @@ async def full_pipeline(audio, target_lang):
         voice_choice = [voices[0]]
     voice_final = f"{voice_choice[0]['ShortName']} - {voice_choice[0]['Locale']}"
 
+    # Step 5: Generate final audio
     audio_out = await text_to_speech(translated, voice_final, 0, 0)
-
-    return text, translated, f"{emotion} / {tone}", audio_out
+    return audio_out
 
 # ----------------------------
 # 6. GRADIO UI
 # ----------------------------
 with gr.Blocks() as demo:
-    gr.Markdown("# 🌍 Speech Translator with Emotions")
+    gr.Markdown("# 🎤 Speech Translator with Emotions")
 
     with gr.Row():
-        audio_in = gr.Audio(sources=["microphone"], type="filepath", label="🎤 Record Speech")
-        target_lang = gr.Dropdown(choices=["English", "Spanish", "French"], value="English", label="Translate to")
+        audio_in = gr.Audio(sources=["microphone"], type="filepath", label="Record Speech")
+        target_lang = gr.Dropdown(choices=["English", "Spanish", "French"], value="English", label="Target Language")
 
-    with gr.Row():
-        stt_out = gr.Textbox(label="📝 Recognized Speech", lines=2)
-        trans_out = gr.Textbox(label="🌐 Translated Text", lines=2)
-
-    with gr.Row():
-        emotion_out = gr.Textbox(label="😊 Detected Emotion & Tone")
-        audio_out = gr.Audio(label="🔊 Final Speech", type="filepath")
+    final_speech = gr.Audio(label="🔊 Final Speech", type="filepath")
 
-    run_btn = gr.Button("🚀 Run Pipeline")
-    run_btn.click(fn=full_pipeline, inputs=[audio_in, target_lang], outputs=[stt_out, trans_out, emotion_out, audio_out])
+    run_btn = gr.Button("🚀 Translate & Speak")
+    run_btn.click(fn=full_pipeline, inputs=[audio_in, target_lang], outputs=[final_speech])
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()