Show HN: Airy – Free, fast, and simple voice content creation | Hacker News Reader

Show HN: Airy – Free, fast, and simple voice content creation

airy.so

46 pointslogin58818 comments

All but one of the voices sounds tinny. The timing and cadence was good though.

Is this intended for anime autodubbing? There's only one voice (Rowan) that is remotely traditional broadcaster-style.

As with seemingly all AI these days - it seems to fail with prosody and simply speaks the very next word with zero regard to the nuance or cadence that author intended, or an understanding of any the words being spoken.

When AI achieves the ability to deliver some of Shakespeare’s greatest soliloquies or monologues, then I’ll pay attention.

Prosody is hard. No AI voice I've heard really nails voice generation with fully smooth and human-like cadence and quality, but they're gradually getting better. Airy voices sound a bit tinny and childish, but even so, they're better than many I've heard, including for the elusive "humanness" quality.

Why did you pick such creepy voices? They are very childlike and weird.

They just sound like anime voices

Right, I’ve never seen an anime, probably for exactly this reason.

There are good ones without the stereotypical voices, I recommend Fullmetal Alchemist Brotherhood.

I bet you're talking about like English dubs. The original japanese voices are diverse. Aizen from Bleach, Hakshaku (Millennium Earl) from D. Grayman, Marshal D. Teach from One-piece, and All Might from my hero academia have deep regal voices.

They're definitely anime-style voices, though most of the female ones are very annoying. I couldn't stand to watch an anime with them.

You know, I never did find out why people dub anime with such unnatural voices.

The voice actors usually try to match the timing of the mouth flaps in the animation. It's hard to do that while also conveying the meaning of what is said correctly (enough) -- and practically impossible to do that while sounding natural in English too.

That doesn't help for sure, but the intonation is ... odd.

Great, Working fast and cool. You can also try to adding some more voices from different parts of the world.

This is cool! What model are you using?

Thanks! Airy runs on a proprietary TTS model that we built in-house, rather than a third-party model.

Wow! Well done that's really impressive.

Can you change the voice? Also, is it possible to vary the emotion in one audio?

This is cool

Reply on news.ycombinator.com