Update app.py

app.py

@@ -752,12 +752,13 @@ from threading import Thread
 
 repo_id = "parler-tts/parler-tts-mini-v1"
 
+import sounddevice as sd  # For real-time audio playback
+
 
 def generate_audio_parler_tts(text):
     description = "A female speaker delivers a slightly expressive and animated speech with a moderate speed and pitch. The recording is of very high quality, with the speaker's voice sounding clear and very close up."
     chunk_size_in_s = 0.5
 
-    
     # Initialize the tokenizer and model
     parler_tokenizer = AutoTokenizer.from_pretrained(repo_id)
     parler_model = ParlerTTSForConditionalGeneration.from_pretrained(repo_id).to(device)
@@ -788,6 +789,9 @@ def generate_audio_parler_tts(text):
         for new_audio in streamer:
             if new_audio.shape[0] == 0:
                 break
+            # Real-time playback of the audio chunk
+            sd.play(new_audio, samplerate=sampling_rate)
+            sd.wait()  # Wait until the audio is played before moving to the next chunk
             yield sampling_rate, new_audio
 
     audio_segments = []
@@ -809,7 +813,6 @@ def generate_audio_parler_tts(text):
 
 
 
-
 def fetch_local_events():
     api_key = os.environ['SERP_API']
     url = f'https://serpapi.com/search.json?engine=google_events&q=Events+in+Birmingham&hl=en&gl=us&api_key={api_key}'