Skip to content

[WIP] Voice commands for Slicer module #69

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
diazandr3s wants to merge 2 commits into
base: main
Choose a base branch
from
Open

[WIP] Voice commands for Slicer module #69

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
adf5dd8
Add voice commands buttons
adiazpinto Feb 20, 2025
349786f
Add docstrings
adiazpinto Feb 20, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
33 changes: 33 additions & 0 deletions plugins/RadCoPilot_Slicer/RadCoPilot.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -166,12 +166,14 @@ def setup(self):
self.ui.serverComboBox.lineEdit().setPlaceholderText("enter server address or leave empty to use default")
self.ui.scanComboBox.lineEdit().setPlaceholderText("enter scan address")
self.ui.fetchServerInfoButton.setIcon(self.icon("refresh-icon.png"))
self.ui.recordPromptButton.setIcon(self.icon("mic.jpeg"))
self.ui.uploadImageButton.setIcon(self.icon("upload.svg"))

# start with button disabled
self.ui.sendPrompt.setEnabled(False)
self.ui.uploadImageButton.setEnabled(False)
self.ui.fetchImageButton.setEnabled(False)
self.ui.recordPromptButton.setEnabled(False)
self.ui.outputText.setReadOnly(True)

# Connections
Expand All @@ -181,6 +183,7 @@ def setup(self):
self.ui.cleanOutputButton.connect("clicked(bool)", self.onClickCleanOutputButton)
self.ui.uploadImageButton.connect("clicked(bool)", self.onUploadImage)
self.ui.fetchImageButton.connect("clicked(bool)", self.onFetchImage)
self.ui.recordPromptButton.connect("clicked(bool)", self.onRecordAudio)


self.updateServerUrlGUIFromSettings()
Expand Down Expand Up @@ -318,6 +321,7 @@ def onClickFetchInfo(self):
self.ui.sendPrompt.setEnabled(True)
self.ui.uploadImageButton.setEnabled(True)
self.ui.fetchImageButton.setEnabled(True)
self.ui.recordPromptButton.setEnabled(True)
# Updating model name
self.ui.appDescriptionLabel.text = self.info

Expand Down Expand Up @@ -453,6 +457,35 @@ def onClickSendPrompt(self):
self.ui.outputText.setText(info['choices'][0]['message']['content'])
logging.info(f"Time consumed by fetch info: {time.time() - start:3.1f}")

def onRecordAudio(self):
'''Handles the voice prompts sent to the server.'''
audioRecorder = qt.QAudioRecorder()

# Select default audio input
audioInput = audioRecorder.audioInputs()[0]
audioRecorder.setAudioInput(audioInput)

# Set output location (use a valid path)
outputLocation = qt.QUrl.fromLocalFile("/tmp/output5.wav")
audioRecorder.setOutputLocation(outputLocation)

# Configure audio settings with compatible codec and container
audioSettings = qt.QAudioEncoderSettings()
audioSettings.setCodec("audio/pcm") # Use "audio/mpeg" for MP3 files
audioSettings.setQuality(qt.QMultimedia.HighQuality)
audioRecorder.setAudioSettings(audioSettings)

# Explicitly set container format (optional)
audioRecorder.setContainerFormat("wav") # Use "mp3" for MP3 files

# Start recording
audioRecorder.record()

# Stop recording after 5 seconds
qt.QTimer.singleShot(5000, audioRecorder.stop)





class RadCoPilotLogic(ScriptedLoadableModuleLogic):
Expand Down
Binary file added plugins/RadCoPilot_Slicer/Resources/Icons/mic.jpeg
View file
Open in desktop
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
7 changes: 7 additions & 0 deletions plugins/RadCoPilot_Slicer/Resources/UI/RadCoPilot.ui
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -180,6 +180,13 @@
</property>
</widget>
</item>
<item>
<widget class="QPushButton" name="recordPromptButton">
<property name="text">
<string>Record Prompt</string>
</property>
</widget>
</item>
</layout>
</widget>
</item>
Expand Down