MiniMax · Voice · premium
MiniMax Speech 2.8 HD
The directable one: emotion selector, speed control, twenty-four languages.
What it costs
| Per 1,000 characters | 4.5 credits |
What it takes
| Voices | 17 |
| Languages | 24 |
| Text limit | 4,000 characters |
When to reach for it
The most controllable voice model in the catalog. It is the only one that carries both a discrete emotion selector and a speed control, across twenty-four languages, which makes it the right choice whenever the *delivery* matters as much as the words.
Its seventeen voices are named for what they sound like (Wise Woman, Deep Voice Man, Calm Woman, Casual Guy), so choosing one is a decision you can make by reading rather than by auditioning all of them. That is a small thing that saves real time against a roster of star names.
It sits at the premium tier and costs more per character than the alternatives, so it is not the model for bulk narration. The pattern that works: draft with Kokoro or Gemini while the script is still moving, and re-render the lines that ship here, where the emotion and pacing can be set deliberately. Pair it with P-Video Avatar or OmniHuman 1.5 and a portrait to turn a directed line into a performance.
MiniMax Speech 2.8 HD is one pick in the composer.
Every model in this catalog runs from the same prompt bar, priced in the same credits. New accounts start with some to spend.
Start picturing