Russian AI voice generator and voice cloning

• Reference recordings for this language are capped at 12 seconds, the same limit used throughout Mayantar.
• Stress is not marked in written Russian and the model infers it. For a heteronym in an ambiguous sentence, rewriting the sentence to disambiguate is more reliable than adding an acute accent.
• Write ё where the word has ё. Russian publishing often prints е instead, and the model then has to guess — «все» and «всё» are different words.
• Latin-script words and acronyms inside Russian text are read as foreign material rather than transliterated. Where you want them read as Russian, write them in Cyrillic.
• Cloning is cross-lingual: a voice cloned from a clip in one language can generate in another on this path. It works, but it is not free — accent from the reference language carries over. Record in the language you intend to publish in unless a foreign accent is the point.

Mayantar ships written prompts for English and the Indian languages; for Russian the recorder offers the English prompts as a starting point, and you are better off reading Russian of your own. Anything works as long as it is you talking normally — introduce yourself, describe what you are working on, read a paragraph of your own script.

Aim to fill most of the 12-second limit, keep it in one take, and include a question if you can: rising intonation is the thing a clone most often lacks when the reference was a flat, careful read.

The checks your clip has to pass — and the specific reasons clips get rejected — are in our guide to recording a reference clip.