Update app.py

app.py

@@ -21,7 +21,12 @@ import logging
 
 app = FastAPI()
 templates = Jinja2Templates(directory="templates")
-
+@app.get("/", response_class=HTMLResponse)
+async def read_root(request: Request):
+    return templates.TemplateResponse(
+        "interface.html",
+        {"request": request, "data": data},
+    )
 # Configure logging
 logging.basicConfig(level=logging.DEBUG)
 # Mock data for your interface
@@ -186,10 +191,17 @@ async def main(
         noise_scale = noise_scale_slider.value
         noise_scale_w = noise_scale_w_slider.value
         auto_play = play.value
-        inferencing(model, config, sid, text, rate, noise_scale, noise_scale_w, auto_play)
+        audio = inferencing(model, config, sid, text, rate, noise_scale, noise_scale_w, auto_play)
+        temp_audio_file = tempfile.NamedTemporaryFile(delete=False, suffix=".mp3")
+        audio.export(temp_audio_file.name, format="mp3")
+    
+    # Rename the temporary audio file based on the text input
+        renamed_audio_file = os.path.join(tempfile.gettempdir(), f"{text_input}.mp3")
+        os.rename(temp_audio_file.name, renamed_audio_file)
 
         # Save the audio as a temporary WAV file
-    return {"message": "Post request received", "data": data}
+    return templates.TemplateResponse("interface.html", {"request": request, "audio_file": renamed_audio_file})
+
 
   #  return {"message": f"Text to synthesize: {text_input}, Speed: {speed_slider}, Play: {play}"}
 
@@ -241,7 +253,6 @@ def phonemes_to_ids(config, phonemes: List[str]) -> List[int]:
     ids.extend(id_map[EOS])
     return ids
 
-@app.get("/generate_audio")
 def inferencing(model, config, sid, line, length_scale = 1, noise_scale = 0.667, noise_scale_w = 0.8, auto_play=True):
     audios = []
     if config["phoneme_type"] == "PhonemeType.ESPEAK":
@@ -278,7 +289,9 @@ def inferencing(model, config, sid, line, length_scale = 1, noise_scale = 0.667,
     sample_rate = config["audio"]["sample_rate"]
     temp_audio_path = os.path.join(tempfile.gettempdir(), "generated_audio.wav")
     sf.write(temp_audio_path, merged_audio, config["audio"]["sample_rate"])
-    return FileResponse(temp_audio_path)
+    audio = AudioSegment.from_mp3(temp_audio_path)
+    return audio
+#    return FileResponse(temp_audio_path)
     # Return the audio file as a FastAPI response
   #  display(Markdown(f"{line}"))
    # display(Audio(merged_audio, rate=sample_rate, autoplay=auto_play))
@@ -376,14 +389,12 @@ def transform(input_data):
 
     return magnitude, phase
 
-@app.get("/", response_class=HTMLResponse)
-async def read_root(request: Request):
-    return templates.TemplateResponse(
-        "interface.html",
-        {"request": request, "data": data},
-    )
 
 
+#@app.get("/")
+#async def read_root(request: Request):
+#   return templates.TemplateResponse("interface.html", {"request": request})
+
 if __name__ == "__main__":
  #   main()
     import uvicorn