It’s possible but I don’t see many advantages to do this 🙂 It will slow down the processing, it will cost you more and also… most major browsers will definitely soon allow to speech-to-text and text-to-speech for free. This is why I don’t do it right away.
But yeah, if at least Whisper API could speak back, it would be a bit more interesting. As for now, it’s mainly useful to transform big files into texts I believe. That said, if more people are interested, I might do it as it’s not complicated. If I do, I believe people will try but most will not actually keep it enabled.
Thread Starter
Anonymous User 18191698
(@anonymized-18191698)
I have to agree with you there as many keyboards and devices already have speech to text built in.
However, i believe adding text to speech via the web speech api or google or azure might be an idea for the future. It would be nice to give voice to the bot.
Yeah, text to speech would be great; if we can do it both ways nicely, it will allow people with disabilities to use it. Of course, I definitely want that! I just want to do it well 🙂
