Gemini-3.5-Transcribe

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.

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 eleven labs. Yes, Voxtral might not reach the best score in the benchmarks, but to me, it just solves a problem. It might not be the best in terms of speed... but that’s not a problem for me.

Happy to test this new model from Google but I’m not sure I’d go with that instead of something that can run so easily in my machine.

"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/models/gemini-3.5-tran...) confirm that the Gemini 3.5 Transcribe model cannot in fact make function calls. I guess the blog post is just using very confusing wording to describe how their consumer assistant/chatbot app can both take audio input via Gemini 3.5 Transcribe and then call other things as needed. Or maybe that bullet point was meant to be for a different model announcement and somebody made an editing error.

I've been testing it on Pixel 11 Pro and I mostly dislike it. It is convenient when you have something long to say without thinking about it first. But the main issue is when you want to say something precise with specific wording it might "simplify" it and break the meaning.

Something like "I hesitated to check it, I should have verified" => "I should have verified" (The "I hesitated..." is removed but I said it because I wanted to let the person know that I thought about it earlier)

I tried the sentence few times and it always removed the first part.

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 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.

I've been using Wispr Flow on my pixel 9 and I like it. It does the things that Rambler says it's supposed to do but it's available on my Pixel 9 unlike rambler that's currently only available for pixel 11.

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.

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.

That's really impressive! It says it's available in GBoard on Android but I don't see it yet. I assume like most Google features it will be a rolling release over the course of several months, can't wait to try it some day.

Just added this to my benchmark site: https://multilingualsttbench.com/

It doesn't reach the frontier in either latency or accuracy for ai multilingual conversations.

Still more expensive and worse performing than ElevenLabs Scribe, unfortunately. Not sure who's the target audience for this.

Annoying that they don't include pricing info in new models, here it is [1]:

Gemini 3.5 Transcribe Live (Per 1M tokens in USD):

    Input: $3.50 or $0.005/min* (audio)
    Output: 21.00 or $0.004/min* (text)

Gemini 3.5 Transcribe:

    Input: $2.00 or $0.003/min* (audio)
    Output: $12.00 or $0.002/min* (text)

[1] https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-tra...

I am not sure if "Word Error Rate" captures what has always been wrong with transcription. My biggest complaint is that it inserts sentence breaks in random places, then fails to evaluate the result, even though it is obviously wrong. Then I have to go fix it which can be harder than having just typed it myself, due to the difficulty of positioning the Android cursor, the fact that it automatically capitalizes if you delete a capital letter, etc. And much of the time I fail to notice the errors until later.

Hopefully YouTube automatic captions improve with this

Very impressive, including the ability to hit fn in any text field and say "generate an image ...".

I'd love to know how this handles proper subtitle formatting. I'm in the process of learning many languages, and being able to cross check my own understanding with film and video would be fantastic.

Where does the compute happen?

I suppose it's a cloud thing?

Does somebody knows what top locales list is sampled from? their own usage data? Also when they will use their AI to give better directions in Waze?

[flagged]

[flagged]

[flagged]