~27ms encoder inference on Apple Silicon GPU for 10s audio (110M model) — 96x faster than CPU.
Limits to 150,000 words，更多细节参见51吃瓜
await for (final response in chat.generateChatResponseAsync()) {，推荐阅读Line官方版本下载获取更多信息
▲图片来源：X@vamsibatchuk｜提示词来源：X@TechieBySA，推荐阅读爱思助手下载最新版本获取更多信息
* Colorado residents may no longer use DB48x after Jan 1st, 2028.