Add gong to the output sound

ansage.py

@@ -5,29 +5,36 @@ from TTS.api import TTS
 device = "cuda" if torch.cuda.is_available() else "cpu"
 
 # List available 🐸TTS models
-print(TTS().list_models())
+#print(TTS().list_models())
 
 # Initialize TTS
 tts = TTS("tts_models/multilingual/multi-dataset/xtts_v2").to(device)
 
 # List speakers
-print(tts.speakers)
 
-# Run TTS
-# ❗ XTTS supports both, but many models allow only one of the `speaker` and
-# `speaker_wav` arguments
-
-# TTS with list of amplitude values as output, clone the voice from `speaker_wav`
-#wav = tts.tts(
-#  text="Hello world!",
-#  speaker_wav="my/cloning/audio.wav",
-#  language="en"
-#)
+# Configure output path 
+output_path = "output.wav"
 
 # TTS to a file, use a preset speaker
 tts.tts_to_file(
-  text="Hallo Oliver, herzlichen Glückwunsch zur erfolgreichen Entlastung",
-  speaker_wav="./0248.wav",
-  language="en",
-  file_path="output2.wav"
+  text="Verehrte Fahrgäste, das heutige Besäufnis wird Ihnen gesponsert von, Rheinmetall",
+  speaker_wav=["./0248.wav"],
+  language="de",
+  file_path=output_path
 )
+
+# Process Audio (geklaut von meinem guten Freund flon)
+
+from pydub import AudioSegment
+from pydub.utils import make_chunks 
+
+audio = AudioSegment.from_wav(output_path)
+audio = audio.set_channels(1)
+audio = audio.set_sample_width(2)
+audio = audio.set_frame_rate(16000)
+
+silence = AudioSegment.silent(duration=1000)
+gong = AudioSegment.from_wav("./513_1.wav")
+
+audio = silence + gong + audio 
+audio.export(output_path, format="wav")