(github.com)

652 points toebee | 1 comments | 21 Apr 25 17:07 UTC | HN request time: 0.865s | source

Show context

zhyder ◴[21 Apr 25 20:28 UTC] No.43756118[source]▶

V v cool: first time I've seen such expressiveness in TTS for laughs, coughs, yelling about a fire, etc!

What're the recommended GPU cloud providers for using such open-weights models?

1. toebee ◴[22 Apr 25 01:21 UTC] No.43758250[source]▶

Thanks you!! We personally used Quickpod and Runpod the most. But you can try it now on HF Spaces without spinning up GPUs yourself!

Show HN: Dia, an open-weights TTS model for generating realistic dialogue