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

61–70 of 140 posts

Re: Gemini-3.5-Transcribe

#61

Post by low_tech_punk »

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…

Soniox website has a live comparison demo: https://soniox.com/compare-stt

For me, Gemini-3.5-Transcribe actually has slightly lower latency. Kudos to Soniox for both paying their competitor and letting them win. But yes, Soniox is much cheaper.

Re: Gemini-3.5-Transcribe

#62

Post by sgt »

low_tech_punk wrote: post #61
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…

Soniox website has a live comparison demo: https://soniox.com/compare-stt For me, Gemini-3.5-Transcribe actually has slightly lower latency. Kudos to Soniox for both paying their competitor and letting them win. But yes, Soniox is much cheaper.

Interesting, I uploaded a voice recording from a meeting I had recorded with a relatively cheap microphone.

Soniox came out really good. OpenAI started getting some things very wrong and even introduced some German. Google did okay but cut off the start by several seconds.

What's Soniox doing (left most) that's making it so good ? It was also the only one that could distinguish between the speakers.

Re: Gemini-3.5-Transcribe

#64

Post by ameliaquining »

Nifty3929 wrote: post #59
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.

STT models just turn audio into text, though; they don't interpret what the text means or figure out how to translate it into other representations like function calls. You would use a general-purpose model for that.

Re: Gemini-3.5-Transcribe

#66

Post by orbital-decay »

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…

This problem is legitimately hard and needs high cognitive abilities. Even the biggest generalist models struggle with memes and lingo salad that sound immediately intuitive for an out-of-the-loop human, and I'm talking about text comprehension. Modern models are optimized for decision making and are worse in that than old ones optimized for creative writing, but those also struggled.

You should probably not expect a small STT model like Voxtral or Parakeet to do any better, unless it's laser focused on that area in particular and sucks in everything else.

Re: Gemini-3.5-Transcribe

#67

Post by ghm2199 »

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…

Realtime + Voice AI usecases is where latency is most important. I use Handy on my desktop and i can tolerate a latency of a few seconds every now and then. Your P99 should on TTFB should be really low to compete for voice ai realtime

Re: Gemini-3.5-Transcribe

#68

Post by Frannky »

zhivota wrote: post #37

I'd certainly use Gemini API a lot more if I could figure out how to give them money and they give me tokens. The whole tier nonsense is just insane hoop jumping compared to their competition.

I use OpenRouter. Interacting with the Google Cloud Console is pure pain.

Re: Gemini-3.5-Transcribe

#69

Post by Doohickey-d »

film42 wrote: post #11

Curious if this suffers from the same hallucination problems as Chirp or not. For example, if you pass chirp some audio with noise or even no audio, it will barf text at you like "I don't know. I don't know. I don't know." until a request timeout fires after like 10 minutes. It's... really bad. For this reason, we've moved back to Whisper for timestamp accuracy and then Gemini Flash for transcription correction.

Yes, that's sort of our strategy as well: for us accuracy (and following a style guide, and extracting on-screen text from video) is important. So we do a first pass with whisper to get the word timestamps, and the pass the same audio (chunked in case of longer ones) to Gemini (pro, not this model), to transcribe without timestamps. After that you can transfer the timestamps from whisper to the timestamp-less Gemini text, by looking for runs of identical words in both and fudging timestamps for the other words I'm between a bit. Works quite well, and I'll be tesing this model to see if it can replace Whisper.

Re: Gemini-3.5-Transcribe

#70

Post by guiambros »

satvikpendem wrote: post #56
selcuka wrote: post #42

Earlier quoted context omitted.

> 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.

Except when you have multiple participants in the same room -- which happens pretty frequently in many business environments.
Post reply on HN