SohomToom commited on
Commit
7b0353e
·
verified ·
1 Parent(s): 87798cd

Upload 2 files

Browse files
Files changed (2) hide show
  1. app.py +28 -0
  2. requirements.txt +3 -0
app.py ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import gradio as gr
2
+ from docx import Document
3
+ from TTS.api import TTS
4
+ import tempfile
5
+
6
+ # Load TTS model once
7
+ tts = TTS(model_name="tts_models/en/vctk/vits", progress_bar=False, gpu=False)
8
+
9
+ def extract_text(docx_file):
10
+ doc = Document(docx_file)
11
+ return "\n".join([para.text for para in doc.paragraphs if para.text.strip()])
12
+
13
+ def generate_audio(docx_file):
14
+ text = extract_text(docx_file.name)
15
+ with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as temp_audio:
16
+ tts.tts_to_file(text=text, file_path=temp_audio.name)
17
+ return temp_audio.name
18
+
19
+ # Gradio UI
20
+ interface = gr.Interface(
21
+ fn=generate_audio,
22
+ inputs=gr.File(file_types=[".docx"], label="Upload your DOCX script"),
23
+ outputs=gr.Audio(label="Realistic Voiceover", type="filepath"),
24
+ title="DOCX to Voiceover (Offline, Realistic)",
25
+ description="Upload a .docx script and get a realistic WAV voiceover using Coqui TTS."
26
+ )
27
+
28
+ interface.launch()
requirements.txt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ gradio
2
+ python-docx
3
+ TTS