speech generation (github.com)

4 points by unliftedq 4mo ago ↗ HN

Imagent gives AI agents the ability to generate images, video, and speech as a first-class step in their workflows, behind a single interface that hides the differences between providers and models

1 comment

[ 3.3 ms ] story [ 13.8 ms ] thread

ankurchrungoo 4mo ago ↗

I have been working on something similar but also quite different, and I find this interesting. Do you foresee that the cost of video generation, for example, be managed by the user via his own API keys configured for different platforms?