CsabaConsulting / InspectorGadgetApp

Open Multi-Modal Personal Assistant
MIT License
3 stars 1 forks source link

Explore completely hands free operations instead of push to talk / image #33

Open MrCsabaToth opened 4 weeks ago

MrCsabaToth commented 4 weeks ago

Currently the app operates in a push to talk manner (also push to signal the end of talk, the native STT often times cuts the session short while I'm still speaking). It'd be the best to have completely hand free operations somehow. The activation can be by keyword. We could also utilize gesture detection in case of multi modal operation. Even in the demo video the multi modal scenes were hard to record.

MrCsabaToth commented 2 weeks ago

Roman Jaquez at https://gdg.community.dev/events/details/google-gdg-surrey-presents-beyond-chatbots-unlocking-geminis-potential-through-flutter/ told me that the https://pub.dev/packages/speech_to_text plugin support voice activation. So we could offer that when the user enables Android native Speech Services and this would not be usable in translation mode.