The voice that explains
The explanation is spoken by neural voices generated in the cloud, paragraph by paragraph, and saved with the file. Your computer or phone only plays the audio: there is nothing to download or install.
The voices
Voices belong to a language, not to the app: a Spanish voice reading English sounds like someone reading a language they do not speak. The ones on offer are those of the presentation's language, which is the language of the explanation, and there are two in each.
| Language | Voices | Selected by default |
|---|---|---|
| Spanish | Fil (masculina) and Mina (femenina) | Fil |
| English | Fil (male) and Mina (female) | Fil |
They share names across both languages, but they are not the same voice translated: each language has its own, native to that language. And yes, Mina is also the name of the character who explains things to you, even though the voice that comes selected is Fil.
You change the voice in Settings, in the viewer's dock while Mina is explaining, at any time, and each file keeps the voice you were listening to it with. Changing it does not think the explanation through again: the script is already written, and what gets done again is saying it, starting with the slide you are on.
Speed
From 0.8× to 1.75×, in seven steps: 0.8×, 0.9×, 1×, 1.15×, 1.3×, 1.5× and 1.75×. Speed does not regenerate anything: it is the audio that is already there, played faster or slower, so you can change it mid sentence without waiting. The time left to finish the file, above the script, is worked out at the speed you picked.
Straight through
When the last idea of the slide ends, and the question if they are on, it moves to the next slide and keeps going. That is what turns Filmina into something you listen to straight through instead of something you keep asking for one slide at a time. To stay on a slide, pause.
If the next slide is still being prepared, Mina tells you what she is up to and the slide starts on its own as soon as it is ready. You can also pause, resume and skip slides from the lock screen or your headphones.
When you ask Mina something while the explanation is playing, the voice pauses. When you close the chat she 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
The audio for each paragraph is generated once and saved with the file. Listening to a slide again, going back, or opening the file another day on another device plays what was already there: nothing is generated again and no explanation minutes from your plan are used.
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 rewritten because you flagged it as wrong. How many minutes each plan includes is in Limits and on the pricing page.
In silent mode the explanation is written but not spoken, and it uses no minutes. The voice is only generated when you switch to narrated.
The summary's voice
A presentation's summary can be listened to as well, topic by topic, in the voice you listened to the presentation with; if you have not listened to it yet, in the one that comes selected. The summaries you make with Convert to are read in the voice that comes selected for their language. In a conversation Podcast, Fil and Mina talk it through. They are in Summaries, maps and podcasts.