Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Gemini-3.5-Transcribe

blog.google

Post reply on HN
Print view View original

51–60 of 140 posts

Re: Gemini-3.5-Transcribe

#51

Post by pomtato »

crossroadsguy wrote: post #39
Lucasoato wrote: post #21

I’ve tested at least 20 STT models in a benchmark I’ve set up with German, Italian and English voices from meetings in my company. The voices contained very industry specific words, the languages changed from one sentence to another, sometimes words in a language were mentioned while a discussion was in another. The only local model that satisfies me is Voxtral Mini 3b, the only paid API that is slightly better is el…

Do you use it on a desktop? Mac by any chance? What's your setup? I've been looking to find a simple and fast dictation app for English but almost everything I've tried (from Handy to many apps, eg some with Whisper in their names, after the model I assume) just don't work well. Apple's offering is worse than those though. I even tried with local enhancement models.

You should give VoiceInk[1] a go. It works great and has decent latency.

https://github.com/Beingpax/VoiceInk

Re: Gemini-3.5-Transcribe

#52

Post by huijzer »

ameliaquining wrote: post #48
anukin wrote: post #44

Earlier quoted context omitted.

Probably written using Gemini which hallucinated.

Pangram says human: https://www.pangram.com/history/a69f9b74-eb46-44b9-a087-7822...

Maybe I missed something, but isn’t it impossible to detect whether something is written by AI or not? A human on a bad day can write like AI while an AI on a good day can write like a human.

Re: Gemini-3.5-Transcribe

#53

Post by anton000 »

Lucasoato wrote: post #21

I’ve tested at least 20 STT models in a benchmark I’ve set up with German, Italian and English voices from meetings in my company. The voices contained very industry specific words, the languages changed from one sentence to another, sometimes words in a language were mentioned while a discussion was in another. The only local model that satisfies me is Voxtral Mini 3b, the only paid API that is slightly better is el…

have you tried groq whisper-turbo? works well for me for multiple different languages

Re: Gemini-3.5-Transcribe

#54

Post by mediaman »

huijzer wrote: post #52
ameliaquining wrote: post #48

Earlier quoted context omitted.

Pangram says human: https://www.pangram.com/history/a69f9b74-eb46-44b9-a087-7822...

Maybe I missed something, but isn’t it impossible to detect whether something is written by AI or not? A human on a bad day can write like AI while an AI on a good day can write like a human.

No, that's not correct for any reasonable definition of "impossible." Look up pangram's accuracy ratings. It's not perfect, but it's pretty good. LLMs in fact leave very distinguishing traces of their logit distributions in the text they write. It's one of the reasons why it's so easy for humans to also smell them.

It is possible to trick pangram - they bias toward a low false positive and a higher false negative - but it is not true that it is essentially random.

Re: Gemini-3.5-Transcribe

#55

Post by ameliaquining »

huijzer wrote: post #52
ameliaquining wrote: post #48

Earlier quoted context omitted.

Pangram says human: https://www.pangram.com/history/a69f9b74-eb46-44b9-a087-7822...

Maybe I missed something, but isn’t it impossible to detect whether something is written by AI or not? A human on a bad day can write like AI while an AI on a good day can write like a human.

https://bfi.uchicago.edu/wp-content/uploads/2025/09/BFI_WP_2...

Re: Gemini-3.5-Transcribe

#56

Post by satvikpendem »

selcuka wrote: post #42
satvikpendem wrote: post #41

Still no real time diarization beyond 3 people (and even then experimental) when others do it very well, like Soniox and Deepgram. For something like meeting notes this is critical. Not sure what the issue is to implement it, maybe that's not Google's use case in mind and rather it's about personal Rambling as the feature on Pixels shows, which uses this model.

> maybe that's not Google's use case in mind That would be interesting when they also own Google Meet.

Yes, I specifically avoided mentioning that because they don't need to diarize from audio directly as they know exactly which participant is speaking at all times.

Re: Gemini-3.5-Transcribe

#57

Post by Frannky »

I don't really need this model, but I needed a fast my voice to command thing, and Gemini flash 2.5 was extremely effective(low latency, high speed).

No need to go from audio to text to reasoning, just from audio to output json for running a command via adb automatically and it's working crazy good.

Re: Gemini-3.5-Transcribe

#58

Post by lnalx »

I personally tested all the STT models for my real-time translator (https://fliptalk.ai). From language detection and accuracy in a noisy environment to the most important point: latency.

At the moment, Soniox STT v5 is definitely the best, and I'm impressed by its performance. It's good that Google released Gemini-3.5-Transcribe, and it beats every other model on accuracy, but it definitely needs a bit more work on latency, which is the most important factor for STT apps.

Re: Gemini-3.5-Transcribe

#59

Post by Nifty3929 »

ameliaquining wrote: post #43

"Function calling: The model can delegate complex tasks (such as image generation and file analysis) to other Gemini models via function calls. Currently available in the Gemini macOS app." This confused the heck out of me because it makes it sound like the STT model can make function calls in order to execute arbitrary tasks, which wouldn't make any sense. The developer docs ( https://ai.google.dev/gemini-api/docs/m…

Remember that function calling doesn’t mean that the model is actually calling a function for you: what it does it interpret the intent, then return back to the application the function and arguments, then the application runs the function with those arguments.

Think voice control for your device. You speak, and it returns back instructions ( a function and arguments) for your device to be execute.

Re: Gemini-3.5-Transcribe

#60

Post by decimalenough »

lnalx wrote: post #58

I personally tested all the STT models for my real-time translator ( https://fliptalk.ai ). From language detection and accuracy in a noisy environment to the most important point: latency. At the moment, Soniox STT v5 is definitely the best, and I'm impressed by its performance. It's good that Google released Gemini-3.5-Transcribe, and it beats every other model on accuracy, but it definitely needs a bit more work o…

Depends on your use case. If you're transcribing meeting notes, latency is a non-issue.
Post reply on HN