2.2.19

• Added a newest multimodal model: GPT-4 "omni": https://openai.com/index/hello-gpt-4o

2.2.18

• Fix: prevent crash if no audio to play.

2.2.17

• Fix: Added prevent try to play audio if empty output.
• Disabled playing finish event on audio or voice control enabled.

2.2.16

• Escape key now stops response generation and audio output (if playing).
• Voice control options added to the Audio menu.
• Added cache on disk for generated static audio content.
• Added plugin translations for other languages.

2.2.15

• Added audio output stop on audio input start.
• Added notify about unrecognized command.
• Voice control improvements.

2.2.14

• Added a 'Voice Control (inline)' plugin that allows for voice command control directly during a conversation.
• Added configuration in 'Settings -> Accessibility' for a blacklist of actions available as voice commands.

2.2.13

• Added stretch to dictionary config fields.
• Removed redundant attachments clear event.

2.2.12

• Improved speech recognition.
• Added minimum required length of audio input.
• Added missing translations.
• Fixed settings hooks triggering on profile switch.

2.2.11

• Added a blacklist for events for the voice event description in settings.
• Added a delay to playing audio when describing events.
• Sorted the list of events in the configuration.

2.2.10

• Extended voice control commands list.
• Extended actions and keyboard shortcuts.