Ultimately, it's limited by the underlying assets. It can only make avatars based on https://getavataaars.com/ which might have been the source of the issues you saw. Could that be it? Source: over 1 year ago

Avataaars Generator - Generate avatars for your customer support and web projects. Source: about 2 years ago

Very nice, great job! Here's another fun one: https://getavataaars.com/. - Source: Hacker News / about 3 years ago

Figure out how to composite SVG variations together to make procedurally genreated player/NPC avatars. The heads come from getavataaars.com and their generator is open source so I want to integrate it directly. Source: over 3 years ago

There's dozens of tools out there for this these days. I'd recommend sonix.ai they give you 30 minutes free. Source: about 1 year ago

Do you have a budget? If so, there's this tool I've worked with called Sonix that generates transcripts of what you feed into it. It's not super accurate, but it's good enough. One of the features is that you can "highlight" chunks of text, and have it spit out an XML that will have a sequence containing only the highlighted text. Source: over 1 year ago

Sonix was the one I used because it had 30 free minutes and the video was only 10-11 minutes long. It seems to have done a really decent job, but not sure if that's because the source audio is pretty clear. Source: over 1 year ago

Sonix.ai does many languages and is quite good. Source: over 1 year ago

I am struggling with this as well, but one good tool for me has been sonix.ai, which can transcribe pretty well (posted a little while ago about it). Source: about 2 years ago