Japanese AI voice generator and voice cloning

• Reference recordings for this language are capped at 12 seconds, the same limit used throughout Mayantar.
• Kanji readings are inferred from context. For a proper noun that must be read a specific way, writing it in hiragana or katakana forces the reading — this is the standard fix and it is what Japanese publishers do with furigana.
• Pitch accent is reproduced from context and from your reference recording; there is no notation for it in the input.
• Numbers and counters follow Japanese counter rules, which depend on what is being counted. Writing the counter word explicitly (三本, 三枚) is more reliable than a bare numeral.
• 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 Japanese the recorder offers the English prompts as a starting point, and you are better off reading Japanese 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.