Video wird geladen...
Video konnte nicht geladen werden
Having fun playing with new native audio capabilities in Gemini 1.5 Pro! ♊ Here’s a demo using audio from the #GoogleIO keynote with examples you can try: transcription, word-level timecodes, and searching audio by drawing. (🔊Video has sound)
77,097 Aufrufe • vor 2 Jahren •via X (Twitter)
9 Kommentare

Word-level timecodes let you make fun things like this. (🔊Video has sound) My prompt: Find sentences that contain "pickleball" and cite the sentence start and end times. Then give me the exact timecode when the word "pickleball" starts within that sentence. Results will vary and timecodes might not always be correct, so definitely experiment with your own prompts in Google AI Studio. Learn more:

Nifty video scrubber frontend tool made by @trippedout + @GrantCuster. It's neat to be able to interact directly with the timecodes the model gives us.

This is great capability-Can you please share the note book ?

Thanks! I'll message you and send the prompts I used in AI Studio.

I wonder how well these would work with 1.5 Flash

I've tried similar prompts with Gemini 1.5 Flash and gotten generally solid results too.

Do they support diarization already?

I'm not sure, I haven't tried that.

amazing



