Portuguese AI voice generator and voice cloning

• Reference recordings for this language are capped at 12 seconds, the same limit used throughout Mayantar.
• Nasal vowels are marked in the orthography (ã, õ, -m, -n) and are read as written. Dropping a tilde changes the word: "pao" is not "pão".
• The written accent distinguishes minimal pairs — avô and avó, por and pôr. Type them; the model pronounces what is on the page.
• Brazilian and European Portuguese share this page and this language option. The variety you get is the variety in your reference clip, not a setting.
• 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 Portuguese the recorder offers the English prompts as a starting point, and you are better off reading Portuguese 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.