Update app.py

app.py

@@ -9,6 +9,7 @@ from TTS.utils.generic_utils import get_user_data_dir
 
 import gradio as gr
 from scipy.io.wavfile import write
+from pydub import AudioSegment
 
 os.environ["COQUI_TOS_AGREED"] = "1"
 tts = TTS("tts_models/multilingual/multi-dataset/xtts_v1")
@@ -40,11 +41,11 @@ def stream_audio(synthesis_text):
 
     for i, chunk in enumerate(chunks):
         print(f"Received chunk {i} of audio length {chunk.shape[-1]}")
-        bytes_wav = bytes()
-        byte_io = io.BytesIO(bytes_wav)
-        write(byte_io, 24000, chunk.detach().cpu().numpy().squeeze())
-        result_bytes = byte_io.read()
-        yield result_bytes
+        out_file = f'{i}.wav'
+        write(out_file, 24000, chunk.detach().cpu().numpy().squeeze())
+        audio = AudioSegment.from_file(out_file)
+        audio.export(out_file, format='wav')
+        yield out_file
 
 demo = gr.Interface(
     fn=stream_audio,