No audio? 🤐
#45
by Iwaku-Real - opened
Most of us had thought Edge would have the full multimodal capabilities of Nano and Super but at a much smaller scale that is even more feasible to deploy on many consumer and production systems alike. However, the current release of Edge does not provide any support of audio, neither in the Reasoner nor Generator, and it could be leaving a lot of potential users forced to either scale up to Nano or implement some sort of STT, etc. Would you consider at some point updating Edge with audio support so that it is fully multimodal? It would be excellent