Update app.py

app.py

@@ -244,10 +244,21 @@ def on_src_or_tgt_lang_change(src_lang_value, tgt_lang_value, pnc_value):
 		)
 	return src_lang, tgt_lang, pnc
 
+def txt2speech(text):
+    print("Initializing text-to-speech conversion...")
+    API_URL = "https://api-inference.huggingface.co/models/espnet/kan-bayashi_ljspeech_vits"
+    headers = {"Authorization": f"Bearer {HF_TOKEN}"}
+    payloads = {'inputs': text}
+
+    response = requests.post(API_URL, headers=headers, json=payloads)
+    
+    with open('audio_out.mp3', 'wb') as file:
+        file.write(response.content)
+
 def main(audio_filepath, src_lang, tgt_lang, pnc):
     translated = transcribe(audio_filepath, src_lang, tgt_lang, pnc)
     answer = llm_pipe(translated, **generation_args)
-    return answer[0]['generated_text']
+    return [answer[0]['generated_text'], 'audio_out.mp3']
     
     
 
@@ -306,11 +317,13 @@ with gr.Blocks(
 				elem_id="model_output_text_box",
 			)
 
+            audio_out = gr.Audio(label="Generated Audio", type="numpy", elem_id="audio_out")
+
 
 	go_button.click(
 		fn=main, 
 		inputs = [audio_file, src_lang, tgt_lang, pnc],
-		outputs = [model_output_text_box]
+		outputs = [model_output_text_box, audio_out]
 	)
 
 	# call on_src_or_tgt_lang_change whenever src_lang or tgt_lang dropdown menus are changed