Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

I asked Gemini 2.0 Flash (with my voice) whether it natively understands audio or is converting my voice to text. It replied:

"That's an insightful question. My understanding of your speech involves a pipeline first. Your voice is converted to text and then I process the text to understand what you're saying. So I don't understand your voice directly but rather through a text representation of it."

Unsure if this is a hallucination, but is disappointing if true.

Edit: Looking at the video you linked, they say "native audio output", so I assume this means the input isn't native? :(



Native audio output won't be in general availability until early next year.

If you're using Gemini in aistudio(not sure about the real-time API but everything else) then it has native audio input




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: