Improve TTS text normalization
Incoming voice text is normalized and improved after capture.
Changelog (46)
Whenever there is a new functionality for Skipper being added or revised, it is recorded in the Changelog. Sometimes it is hard to describe in a simple summary what skipper can do. Hopefully through these snippets, Skipper capabilities can be explained with more detail.
Added HD vision session admission
Vision observations are added to the main session for processing.
Added HD camera vision observation prototype
Initial HD Camera Drivers and Vision functionality was created and tested.
Added wake acknowledgement voice cues
Wake cues for different aspects of voice input were added.
Added TTS benchmark tools
Tools were added for Text To Speech benchmarking.
Centralized runtime config defaults
All config values are centralized for a more organized functionality.
Added AI model warmup
All used models during a session are now warmed up from start for faster responses.
Added streamed LLM voice output integration
For faster feedback, the sessions now have Stream capability in Chat and Voice.
Added conditional shared embedding cache
For faster sessions, the retrieval is cached to save few milliseconds.