Hi,
Where can I find documentation on what’s in “gpt-4-1106-previw” model and what’s not in “gpt-4 model”.
Thanks.
Hi,
Where can I find documentation on what’s in “gpt-4-1106-previw” model and what’s not in “gpt-4 model”.
Thanks.
Hi is this what you are looking for?
yeah, exactly what I was looking for, thank you.
@lachie1 a side note. tts is nice, along the same line of thought, I wonder if the reverse “stt”, speech-to-text is doable. think about this, your eyes are tired, you don’t want to type any more, instead, you want to talk to the bot or the like and get response and so on…
I think what you are referring to this OpenAI’s Whisper model.
Blog post about Whisper
hmm, not exactly, probably I should say, voice to text, to be accurate. That is, if you speak to the machine/bot or whatever, it understands you and takes an action (based on what you say/said).
Having said that, good to know the “whisper” feature/api as well, appreciated.
@SprinterOz thanks for the response, today I went through the entire “whisper” page, the following is interesting: ```
transcribe(filepath, prompt=“ZyntriQix, Digique Plus, CynapseFive…”)