Create tts_singing.py

tts_singing.py

@@ -0,0 +1,17 @@
+from TTS.api import TTS
+from pydub import AudioSegment
+import os
+
+tts = TTS(model_name="tts_models/en/ljspeech/tacotron2-DDC", progress_bar=False, gpu=False)
+
+def generate_singing(text, filename="vocals.wav"):
+    tts.tts_to_file(text=text, file_path=filename)
+    
+    # Apply pitch shift (to make it more "sung")
+    sound = AudioSegment.from_file(filename)
+    pitched = sound._spawn(sound.raw_data, overrides={
+        "frame_rate": int(sound.frame_rate * 1.25)  # pitch up
+    }).set_frame_rate(sound.frame_rate)
+
+    pitched.export(filename, format="wav")
+    return filename