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

I inserted the non-verbal command "(pauses)" in the middle of a sentence and I think I caused it to have an aneurysm.

https://i.horizon.pics/4sEVXh8GpI (27s)

It starts with an intro, too. Really strange

I have a hunch they're pulling data from radio shows to give it that "high quality" vibe. Tried running it through this script and hit some weird bugs too:

    [S1] It really sounds as if they've started using NPR to source TTS models
    [S2] Yeah... yeah... it's kind of disturbing (laughs dejectedly).
    [S3] I really wish, that they would just Stop with this.

https://i.horizon.pics/Tx2PrPTRM3

That's certainly unusual ...

You hittin them balloons again, mate ?

That was... amazing.

It even added an extra f-word at the end. Still veeery impressive

Just noticed he says dejectedly too

Oh brother imagine using this and noticing 4 months in that it randomly throws f-words for flavor at your users

The “Yeah…” followed by an uncomfortably long pause then a second “Yeah…” killed me.

I think it also said "maaan" at the end of the previous line. And speaks out lout the "dejectedly".

[pauses] i think i heard demons