You're right, this is not solvable with regular LLMs. It's not possible to mimic natural conversational rhythm with a separate LLM generating text, a separate text-to-speech generating audio, and a separate VAD…
According to the technical paper (https://goo.gle/GeminiPaper), Gemini Nano-1, the smallest model at 1.8B parameters, beats Whisper large-v3 and Google's USM at automatic speech recognition. That's very impressive.
You're right, this is not solvable with regular LLMs. It's not possible to mimic natural conversational rhythm with a separate LLM generating text, a separate text-to-speech generating audio, and a separate VAD…
According to the technical paper (https://goo.gle/GeminiPaper), Gemini Nano-1, the smallest model at 1.8B parameters, beats Whisper large-v3 and Google's USM at automatic speech recognition. That's very impressive.