ChatGPT 支持多模态

[mtr]

ChatGPT 支持了多模态，能力逐步开放。包括：识别图片内容、识别语音、生成语音。支持中文语音识别和生成中文语音，但是生成的中文语音稍微有点老外说中文的口音。

https://gorden-sun.notion.site/9-26-AI- ... 40dbbc255c

[mtr]

ChatGPT can now see, hear, and speak. Rolling out over next two weeks, Plus users will be able to have voice conversations with ChatGPT (iOS & Android) and to include images in conversations (all platforms).

https://twitter.com/OpenAI/status/1706280618429141022

[joe]