[Playtime Session] Implement DaVoice input functionality for hot keywords #95
Labels
dev-work
Issues that need to be developed
playtime-session
All the issues related to the playtime session development
Purpose
Enable interactive voice-based commands using the DaVoice model for real-time user interactions during playtime sessions.
User story
As a user, I want the app to identify special keywords during playtime sessions such as: to repeat instructions previous instructions, pausing, going to the next instructions, or generating a new activity, so the interaction feels natural and personalized.
Acceptance criteria:
Mic button activates voice input using DaVoice model to capture real-time user queries/commands like 'Repeat', 'Next', and 'Pause'.
If the user gives the 'Repeat' command, then the agent fetches the last activity step and reads it aloud.
If the user gives the 'Pause' command, the agent pauses the current activity and provides a user confirmation message, e.g., "Activity paused. Say 'resume' to continue."
If the user gives the 'Next' command, the agent skips the current activity and prompts the Generative AI agent to suggest the next one.
If the voice command is unclear or not recognized, provide a fallback response, e.g., "I didn’t catch that. Could you say it again?".
Nice to have: Use audio feedback to confirm actions, e.g., "Repeating the instruction." or "Skipping to the next activity."
Other notes
Out of scope:
Design notes
Wireframes are here
Design specifics are here
Definition of Done (DoD)
The text was updated successfully, but these errors were encountered: