[jedberg]

Do you have any accuracy benchmarks?

I’ve worked in this space. TTS in a small footprint isn’t the hard part —- it’s doing it accurately that’s hard.

Although for the use cases OP is targeting, lower accuracy may be good enough!

[amelius]

> I’ve worked in this space. TTS in a small footprint isn’t the hard part —- it’s doing it accurately that’s hard.

This actually holds for everything in AI.

[jedberg]

Very true!

[kamranjon]

If you look at this chart here it seems the tiny model has a WER of ~12%… not sure about the micro model:

https://github.com/moonshine-ai/moonshine#when-should-you-ch...

[yorwba]

That's the error rate for STT, not TTS. TTS is generally easier than STT because you only need to produce one valid pronunciation and don't need to handle variation within and between individuals.