Just two weeks ago we tried Russian on v2 for a quick kids medical education video.

About 1/4 prompt samples wouldn't work but instead did one of the following:

- Put a random long pause somewhere in the clip and play the other syllables at 10x speed with the remaining space left in the clip - Stop reading the prompt and start talking in literal simlish: https://www.youtube.com/watch?v=yW4nfveKW5s - Screaming, as in full goat screaming. Not even our resident AI evangelists could defend that one.

There's something very wrong with the Russian one. The first example "Jessica | Tell History", is British woman speaking British English transliterated from Russian. It's absolute murder of the Russian language and painful to listen to.

The second example "Jessica | Record a commercial" is perfect. Confidence restored.

The third example "Laura | Help a client" is back to glass in your ears. This time an American is speaking American English transliterated from Russian.

Yikes. The English sounded fine, but the Russian has serious issues. Either there's a bug in your configuration (I hope) or your evals for Russian are unsound.

Edit: dial back the editorializing.

Romanian sounds awful too, like the TTSes from 15 years ago.

I tried Italian and Greek and the examples range from "acceptable" to "lol wtf"

It's a research preview for now but it should work well in 70+ languages. Voices make a big difference, can you try with a few Russian IVCs?