← Back to context Comment by drakenot 9 hours ago I think voice mode uses weaker models, just an FYI relative to the SOTA 2 comments drakenot Reply SOLAR_FIELDS 2 hours ago Can get around this with a local STT model and use text input but UX is probably clunkier scrollop 8 hours ago Definitely, seems like gpt 3
SOLAR_FIELDS 2 hours ago Can get around this with a local STT model and use text input but UX is probably clunkier
Can get around this with a local STT model and use text input but UX is probably clunkier
Definitely, seems like gpt 3