Allow enable/disable speaker and microphone from UI (#56)

* updated the gdrive link to the latest version
* ui additions for enable/disable functionality

GlobalVars.py

@@ -27,6 +27,7 @@ class TranscriptionGlobals(Singleton.Singleton):
  # Global for determining whether to seek responses from openAI API
  freeze_state: list = None
  freeze_button: ctk.CTkButton = None
+ editmenu: tk.Menu = None
  api_key: str = None
  filemenu: tk.Menu = None
  response_textbox: ctk.CTkTextbox = None

main.py

@@ -99,14 +99,6 @@ def main():
  print('[INFO] Override default speaker with device specified on command line.')
  global_vars.speaker_audio_recorder.set_device(index=args.speaker_device_index)
 
- if args.disable_mic:
- print('[INFO] Disabling Transcription from the Microphone')
- global_vars.user_audio_recorder.disable()
-
- if args.disable_speaker:
- print('[INFO] Disabling Transcription from the speaker')
- global_vars.speaker_audio_recorder.disable()
-
  try:
  subprocess.run(["ffmpeg", "-version"],
  stdout=subprocess.DEVNULL,
@@ -136,6 +128,7 @@ def main():
  model = TranscriberModels.get_model(args.api, model=args.model)
 
  root = ctk.CTk()
+ ui_cb = ui.ui_callbacks()
  ui_components = ui.create_ui_components(root)
  transcript_textbox = ui_components[0]
  global_vars.response_textbox = ui_components[1]
@@ -146,7 +139,7 @@ def main():
  global_vars.filemenu = ui_components[6]
  response_now_button = ui_components[7]
  read_response_now_button = ui_components[8]
-
+ global_vars.editmenu = ui_components[9]
  global_vars.user_audio_recorder.record_into_queue(global_vars.audio_queue)
 
  time.sleep(2)
@@ -155,6 +148,15 @@ def main():
  global_vars.freeze_state = [True]
  global_vars.convo = conversation.Conversation()
 
+ # disable speaker/microphone on startup
+ if args.disable_speaker:
+ print('[INFO] Disabling Speaker')
+ ui_cb.enable_disable_speaker(global_vars.editmenu)
+
+ if args.disable_mic:
+ print('[INFO] Disabling Microphone')
+ ui_cb.enable_disable_microphone(global_vars.editmenu)
+
  # Transcribe and Respond threads, both work on the same instance of the AudioTranscriber class
  global_vars.transcriber = AudioTranscriber(global_vars.user_audio_recorder.source,
  global_vars.speaker_audio_recorder.source,
@@ -189,13 +191,11 @@ def main():
  root.grid_columnconfigure(0, weight=2)
  root.grid_columnconfigure(1, weight=1)
 
- ui_cb = ui.ui_callbacks()
  global_vars.freeze_button.configure(command=ui_cb.freeze_unfreeze)
  response_now_button.configure(command=ui_cb.update_response_ui_now)
  read_response_now_button.configure(command=ui_cb.update_response_ui_and_read_now)
  label_text = f'Update Response interval: {update_interval_slider.get()} seconds'
  update_interval_slider_label.configure(text=label_text)
-
  lang_combobox.configure(command=model.change_lang)
 
  ui.update_transcript_ui(global_vars.transcriber, transcript_textbox)

ui.py

@@ -11,7 +11,6 @@
 import app_logging as al
 import constants
 
-
 root_logger = al.get_logger()
 UI_FONT_SIZE = 20
 last_transcript_ui_update_time: datetime.datetime = datetime.datetime.now()
@@ -45,9 +44,18 @@ def freeze_unfreeze(self):
  root_logger.info(ui_callbacks.freeze_unfreeze.__name__)
  self.global_vars.freeze_state[0] = not self.global_vars.freeze_state[0] # Invert the state
  self.global_vars.freeze_button.configure(
- text="Suggest Responses Continuously" if self.global_vars.freeze_state[0] else "Do Not Suggest Responses Continuously"
+ value="Suggest Responses Continuously" if self.global_vars.freeze_state[0] else "Do Not Suggest Responses Continuously"
  )
 
+ # to enable/disable speaker/microphone when args are given or button is pressed
+ def enable_disable_speaker(self, editmenu):
+ self.global_vars.speaker_audio_recorder.enabled = not self.global_vars.speaker_audio_recorder.enabled
+ editmenu.entryconfigure(2, label="Disable Speaker" if self.global_vars.speaker_audio_recorder.enabled else "Enable Speaker")
+
+ def enable_disable_microphone(self, editmenu):
+ self.global_vars.user_audio_recorder.enabled = not self.global_vars.user_audio_recorder.enabled
+ editmenu.entryconfigure(3, label="Disable Microphone" if self.global_vars.user_audio_recorder.enabled else "Enable Microphone")
+
  def update_response_ui_now(self):
  """Get response from LLM right away
  Update the Response UI with the response
@@ -189,6 +197,12 @@ def create_ui_components(root):
  # Add a "Copy To Clipboard" menu item to the file menu
  editmenu.add_command(label="Copy Transcript to Clipboard", command=ui_cb.copy_to_clipboard)
 
+ # Add "Disable Speaker" menu item to file menu
+ editmenu.add_command(label="Disable Speaker", command=lambda: ui_cb.enable_disable_speaker(editmenu))
+
+ # Add "Disable Microphone" menu item to file menu
+ editmenu.add_command(label="Disable Microphone", command=lambda: ui_cb.enable_disable_microphone(editmenu))
+
  # See example of add_radiobutton() at https://www.plus2net.com/python/tkinter-menu.php
  # Radiobutton would be a good way to display different languages
  # lang_menu = tk.Menu(menubar, tearoff=False)
@@ -230,11 +244,11 @@ def create_ui_components(root):
  update_interval_slider.set(2)
  update_interval_slider.grid(row=2, column=0, padx=10, pady=10, sticky="nsew")
 
- lang_combobox = ctk.CTkOptionMenu(root, values=list(LANGUAGES_DICT.values()))
- lang_combobox.grid(row=3, column=0, padx=200, pady=10, sticky="nsew")
+ lang_combobox = ctk.CTkOptionMenu(root, width=15, values=list(LANGUAGES_DICT.values()))
+ lang_combobox.grid(row=3, column=0, ipadx=60, padx=10, sticky="wn")
 
  # Order of returned components is important.
  # Add new components to the end
  return [transcript_textbox, response_textbox, update_interval_slider,
  update_interval_slider_label, freeze_button, lang_combobox,
- filemenu, response_now_button, read_response_now_button]
+ filemenu, response_now_button, read_response_now_button, editmenu]