Live data from Hacker News

Show HN: Banterai – Talk to any AI celebrity, human-like voice conversations

banterai.app

11–20 of 33 posts

Re: Show HN: Banterai – Talk to any AI celebrity, human-like voice conversations

#11
Great job. I must say that the speech synthesis sounds pretty realistic. I talked with Jobs, Musk and Obama and liked how they sounded and more importantly how they handled the questions. Do you mind sharing the entire stack you used to build this? Very well done!

Re: Show HN: Banterai – Talk to any AI celebrity, human-like voice conversations

#14
post #11

Great job. I must say that the speech synthesis sounds pretty realistic. I talked with Jobs, Musk and Obama and liked how they sounded and more importantly how they handled the questions. Do you mind sharing the entire stack you used to build this? Very well done!

Thanks much appreciated! It was a mixture of some the latest TTS models. Azure speech to text. Gpt ofc. And some other tools for handling conversational stuff (like interruptions).

Re: Show HN: Banterai – Talk to any AI celebrity, human-like voice conversations

#17
post #12

Earlier quoted context omitted.

Gonna go out on a limb and say perhaps the creator of this is a fan.

Absolutely not. Huge hater tbh. Just picked personalities that were of public interest.

I think he's likely more interesting to you than he is to the general public.

You might also consider the gender breakdown — you've got 8 men and 4 women (and only two of those women actually exist).

Re: Show HN: Banterai – Talk to any AI celebrity, human-like voice conversations

#20
post #11

Great job. I must say that the speech synthesis sounds pretty realistic. I talked with Jobs, Musk and Obama and liked how they sounded and more importantly how they handled the questions. Do you mind sharing the entire stack you used to build this? Very well done!

Thanks much appreciated! It was a mixture of some the latest TTS models. Azure speech to text. Gpt ofc. And some other tools for handling conversational stuff (like interruptions).

Nicely done. Does Azure Speech to Text also handle speech synthesis and provide out of the box voices for different characters or you had to build your own model to do this? It's impressive if their service can do it all: speech recognition, speech to text and text to speech and in near real-time. I should take a closer look at the Azure ML stack :)
Post reply on HN