News for hackers. Stuff that matters.

A comment on Trying out Gemini 3 Pro with audio transcription and a new pelican benchmark. Parent comment

Re:Trying out Gemini 3 Pro with audio transcription and a ne... by Workaccount2 on Tuesday November 18, 2025 @03:07PM (#45971339)
My assumption is that Gemini has no insight into the time stamps, and instead is ballparking it based on how much context has been analyzed up to that point.

I wonder if you put the audio into a video that is nothing but a black screen with a timer running, it would be able to correctly timestamp.

[ Parent | on HN ]
Re:Trying out Gemini 3 Pro with audio transcription and a ne... by simonw on Tuesday November 18, 2025 @03:19PM (#45971493)
The Gemini documentation specifically mentions timestamp awareness here: https://ai.google.dev/gemini-api/docs/audio
[ Parent | on HN ]
Re:Trying out Gemini 3 Pro with audio transcription and a ne... by minimaxir on Tuesday November 18, 2025 @03:28PM (#45971592)
Per the docs, Gemini represents each second of audio as 32 tokens. Since it's a consistent amount, as long as the model is trained to understand the relation between timestamps and the number of tokens (which per Simon's link it does), it should be able to infer the correct amount of seconds.
[ Parent | on HN ]