For some reason, in almost every test I did with Gemini 3.5 Live, it classified my Swedish (native) as Dutch. There are similarities between the languages, but still.
It’s pretty good at understanding my broken Mandarin, though.
Gemini-3.5-Transcribe
121–130 of 140 posts
Re: Gemini-3.5-Transcribe
#122Still hanging on to Whisper for transcribing and translating audio in real time locally. I play mmos with Chinese people and paying for translation APIs would get expensive quick.
If anyone has suggestion for fast realtime and good enough alternatives with low vram, since I game at the same time, I'd love to know.
Re: Gemini-3.5-Transcribe
#123Still 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.
Interesting, that doesn't line up with the input/output costs listed on Artificial Analysis?
Re: Gemini-3.5-Transcribe
#124I’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.
I just shipped this free app: https://github.com/scosman/Biscotti
Private offline transcription and summary. Speaker identification, working on voice-prints for identification across the corpus.
Re: Gemini-3.5-Transcribe
#125Honestly the most impressive thing to me was the first video where the guy switches between four languages.... I was like "is he AI?" - very impressive, sir!
Re: Gemini-3.5-Transcribe
#126I use Whisper in combination with Qwen3.8 27b to create Dutch subtitles for Russian videos. I follow Ukrainian channels about the war and I am now able to understand them. In my tests with other languages Voxtral was better then Whisper. Whisper often makes mistakes which I now solve with an extra layer (qwen). Sadly Mistral does not support Ukrainian. I hope this changes! I expect better from a European model
[dead]
Re: Gemini-3.5-Transcribe
#127I built a small little app for a company which transcribes all their customer service calls, does an AI review, makes a podcast of the most problematic ones (they LOVE this.) Probably 20 hours a day of transcription. What are people using for cheap hosted models for this? (I don't want to run my own infrastructure.) I'm currently using Gemini Flash Lite. I don't need real time, it's all batched, clear english... stil…
What system are they using to take / record calls?
I scrape them from their crappy VOIP system as WAV files, then send them through the API....
Re: Gemini-3.5-Transcribe
#128I built a small little app for a company which transcribes all their customer service calls, does an AI review, makes a podcast of the most problematic ones (they LOVE this.) Probably 20 hours a day of transcription. What are people using for cheap hosted models for this? (I don't want to run my own infrastructure.) I'm currently using Gemini Flash Lite. I don't need real time, it's all batched, clear english... stil…
have you tried some of the opensource models?
Recommendations? I have an openrouter account. Just don't know what might be good.
Re: Gemini-3.5-Transcribe
#129May be they should use with Nest Hub Max because whatever powers that "Assistant" feels like something from 2023-2024 at best. Half of the time it can't understand you, the other half just fails to output information...
By subscribing to Gemini AI Pro subscription hoped I would get assistant at the level of Gemini app on my phone and instead got something that Qwen 3.5 9b beats.
Re: Gemini-3.5-Transcribe
#130I recently tested a whole bunch of models (basically whatever was recent and available on openrouter filtering by audio input) for STT for mixed language audio - mostly English mixed with Latvian.
In the end I was basically forced to go with Scribe (v2) it was only one that had consistently high quality across multilingual speech with multiple speakers .
Crucially it correctly identified multiple speakers across hour of audio.
I would love to go with something like Transcribe if it gets close to this type of performance.