The voice that explains

The explanation is spoken with neural voices generated in the cloud, paragraph by paragraph, and kept with the document. Your computer or your phone only plays the audio back: there are no models to download and nothing to install.

The voices

Voices belong to a language, not to the app: a Spanish voice reading English sounds like someone reading in a language they do not speak. The ones on offer are those for the deck's language, which is the language of the explanation, and there are two in each:

• Mina, female. She is the default.
• Mino, male.

They have the same names in Spanish and in English, but they are not one voice translated: each language has its own, native to it. And yes, Mina is also the name of the app's character.

You change the voice from the dock settings, at any time, and each document keeps the voice you have been listening to it with. Changing it does not rethink the explanation: the script is already written and what gets redone is the saying of it.

The speed

From 0.8× to 1.75×, in seven steps. Speed regenerates nothing: it is the audio that already exists, said faster or slower, so you can change it mid-sentence with no wait.

Straight through

When the slide's last idea ends, and the question if questions are on, it moves to the next one and keeps going. That is what turns Filmina into something you listen to straight through instead of something you request one slide at a time. To stay on a slide, pause.

If the next one is still being prepared, Mina tells you so ("Getting the explanation ready") and the slide starts on its own as soon as it is ready.

The same voice also reads the lecture's summary, topic by topic. And when you close the chat while the lecture was playing, it says "Let's continue" and picks the paragraph up from the start, so you do not come back in the middle of a sentence.

Said only once

Each paragraph's audio is generated once and kept with the document. Listening to a slide again, going back, or opening the lecture another day on another device plays what was already there: nothing is generated again and no explanation minutes come off your plan.

What does generate new audio is what has not been said yet: a slide you had not heard, the same one in the other voice, or a paragraph that was rewritten because you flagged it as wrong. How many minutes each plan includes is on the pricing.