Update app.py

app.py

@@ -1,14 +1,33 @@
-from transformers import pipeline
-from IPython.display import Audio
+from melo.api import TTS
 
-# Initialize the text-to-speech pipeline with the desired model
-pipe = pipeline("text-to-speech", model="kotoba-tech/kotoba-speech-v0.1")
+# Speed is adjustable
+speed = 1.0
 
-# Input text
-text = "Don't count the days, make the days count."
+# CPU is sufficient for real-time inference.
+# You can set it manually to 'cpu' or 'cuda' or 'cuda:0' or 'mps'
+device = 'auto' # Will automatically use GPU if available
 
-# Generate speech from text
-narrated_text = pipe(text)
+# English 
+text = "Did you ever hear a folk tale about a giant turtle?"
+model = TTS(language='EN', device=device)
+speaker_ids = model.hps.data.spk2id
 
-# Display the audio
-Audio(narrated_text["audio"], rate=narrated_text["sampling_rate"])
+# American accent
+output_path = 'en-us.wav'
+model.tts_to_file(text, speaker_ids['EN-US'], output_path, speed=speed)
+
+# British accent
+output_path = 'en-br.wav'
+model.tts_to_file(text, speaker_ids['EN-BR'], output_path, speed=speed)
+
+# Indian accent
+output_path = 'en-india.wav'
+model.tts_to_file(text, speaker_ids['EN_INDIA'], output_path, speed=speed)
+
+# Australian accent
+output_path = 'en-au.wav'
+model.tts_to_file(text, speaker_ids['EN-AU'], output_path, speed=speed)
+
+# Default accent
+output_path = 'en-default.wav'
+model.tts_to_file(text, speaker_ids['EN-Default'], output_path, speed=speed)