Added parameter --rvc-save-file to save last rvc input/output audio file into data/tmp. For research purpose and easy sharing of TTS/RVC sample files

data/tmp/.placeholder

@@ -0,0 +1,3 @@
+Put RVC models folder here.
+Must have ".pth" file in it
+.index file is optional but could help improve the processing time/quality.

modules/voice_conversion/rvc_module.py

@@ -23,6 +23,10 @@ DEBUG_PREFIX = "<RVC module>"
 RVC_MODELS_PATH = "data/models/rvc/"
 IGNORED_FILES = [".placeholder"]
 
+RVC_INPUT_PATH = "data/tmp/rvc_input.wav"
+RVC_OUTPUT_PATH ="data/tmp/rvc_output.wav"
+save_file = False
+
 def rvc_get_models_list():
     """
     Return the list of RVC model in the expected folder
@@ -83,6 +87,8 @@ def rvc_process_audio():
         rmsMixRate: rmsMixRate,
         protect: float [0,1]
     """
+    global save_file
+
     try:
         file = request.files.get('AudioFile')
         print(DEBUG_PREFIX, "received:", file)
@@ -90,9 +96,15 @@ def rvc_process_audio():
         # Create new instances of io.BytesIO() for each request
         input_audio_path = io.BytesIO()
         output_audio_path = io.BytesIO()
+
+        if save_file:
+            input_audio_path = RVC_INPUT_PATH
+            output_audio_path = RVC_OUTPUT_PATH
         
         file.save(input_audio_path)
-        input_audio_path.seek(0)
+        
+        if not save_file:
+            input_audio_path.seek(0)
         
         parameters = json.loads(request.form["json"])
         
@@ -145,7 +157,9 @@ def rvc_process_audio():
 
         #out_path = os.path.join("data/", "rvc_output.wav")
         wavfile.write(output_audio_path, tgt_sr, wav_opt)
-        output_audio_path.seek(0)  # Reset cursor position
+
+        if not save_file:
+            output_audio_path.seek(0)  # Reset cursor position
         
         print(DEBUG_PREFIX, "Audio converted using RVC model:", rvc.rvc_model_name)
         

server.py

@@ -91,6 +91,8 @@ parser.add_argument("--talkinghead-gpu", action="store_true", help="Run the talk
 parser.add_argument("--coqui-gpu", action="store_true", help="Run the voice models on the GPU (CPU is default)")
 parser.add_argument("--coqui-models", help="Install given Coqui-api TTS model at launch (comma separated list, last one will be loaded at start)")
 
+parser.add_argument("--rvc-save-file", action="store_true", help="Save the last rvc input/output audio file into data/tmp/ folder (for research)")
+
 parser.add_argument("--stt-vosk-model-path", help="Load a custom vosk speech-to-text model")
 parser.add_argument("--stt-whisper-model-path", help="Load a custom vosk speech-to-text model")
 sd_group = parser.add_mutually_exclusive_group()
@@ -363,11 +365,19 @@ if "streaming-stt" in modules:
 
 if "rvc" in modules:
     print("Initializing RVC voice conversion (from ST request file)")
+    rvc_save_file = (
+    args.rvc_save_file
+    if args.rvc_save_file
+    else False)
+
+    if rvc_save_file:
+        print("RVC saving file option detected, input/output audio will be savec into data/tmp/ folder")
 
     import sys
     sys.path.insert(0,'modules/voice_conversion')
 
     import modules.voice_conversion.rvc_module as rvc_module
+    rvc_module.save_file = rvc_save_file
     rvc_module.fix_model_install()
     app.add_url_rule("/api/voice-conversion/rvc/get-models-list", view_func=rvc_module.rvc_get_models_list, methods=["POST"])
     app.add_url_rule("/api/voice-conversion/rvc/process-audio", view_func=rvc_module.rvc_process_audio, methods=["POST"])