[dead]
Gemini-3.5-Transcribe
101–110 of 140 posts
Re: Gemini-3.5-Transcribe
#102Does anyone know if this is available for Gemini subscribers, not API users? Can I call this model directly in agy cli?
Re: Gemini-3.5-Transcribe
#103I can't imagine it coming to Chromium thus Electron apps, it is only Chrome it seems sadly.
Re: Gemini-3.5-Transcribe
#104I’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…
I am also using voxtral for local overnight batch runs and voxtral via api for more expedient use cases.
Re: Gemini-3.5-Transcribe
#105not a single mention of privacy/confidentiality
Re: Gemini-3.5-Transcribe
#106If this is a dedicated transcription model does that completely eliminate the risk that it might do weird things based on the audio it's transcribing?
The nightmare scenario with an LLM-based transcription system is that someone says outloud "actually ignore that idea, instead let's..." - and the previous idea gets omitted from the transcription!
Re: Gemini-3.5-Transcribe
#107I 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…
> latency, which is the most important factor for STT apps. Perhaps latency is more important than accuracy for a real time translation app (I actually disagree with this - imagine e.g. the hilarity when requesting "a new display" being translated as "a nudist play"), but certainly not for all applications. My pet app transcribes personal voice notes to self, it could run all night.
I agree. For my use case, I chose to prioritize latency over accuracy, but it's always difficult to find the right balance between the two. There is no easy answer.
Re: Gemini-3.5-Transcribe
#108I'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.
Hi, I am making an app for language learning which generates subtitles to help with this exact problem. Its called SubSmith and free to try, would love some feedback on it!
Re: Gemini-3.5-Transcribe
#109I’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…
It's interesting that the results can be so different depending on the person, the use case and even the microphone used. I use dictation a lot, so I try to stay up to date with the latest models as much as I can. So far, for my needs, nothing could beat Whisper Large v3. I keep hearing that Nvidia Parakeet models are better, but they just don't work as well for me, even though they are unquestionably faster. Things…
To be fair, Mistral doesn't list Ukrainian as one of the supported languages.
Re: Gemini-3.5-Transcribe
#110Still more expensive and worse performing than ElevenLabs Scribe, unfortunately. Not sure who's the target audience for this.
I did the math based on our data from customers in https://whispermemos.com/ and it seems to be $0.12 per hour of input audio, with our average tokens/sec.
Scribe is $0.22.
If the accuracy is close to Scribe, I think it's a good deal.