Voices Overview

Every character in your audio story needs a voice. Brainports gives you three ways to find the perfect one.

Three Types of Voices

Preset Voices

Built-in voices that are ready to use immediately. No setup, no waiting. Pick one from the voice picker and start generating audio.

Preset voices are available on all plans, including Free.

Learn more about Preset Voices

Designed Voices

Describe the voice you want in plain English, and the AI creates a unique voice to match. For example: "warm female narrator, mid-30s, slight British accent" or "gruff old pirate captain with a raspy laugh."

Voice design is available on paid plans (Starter, Pro, and Studio).

Learn more about Voice Design

Cloned Voices

Upload a reference audio sample and the AI creates a voice that sounds like a specific person. Perfect for maintaining a consistent brand voice or narrating in your own voice.

Voice cloning is available on paid plans (Starter, Pro, and Studio). Not available on Free.

Learn more about Voice Cloning

Automatic Voice Assignment

When the AI writes your script, it automatically assigns voices to each character. You don't need to pick voices upfront — the AI chooses appropriate voices based on character descriptions in your story.

Change Voices Anytime

You're never locked in. You can:

• Swap a character's voice across the entire script

• Change the voice on a single segment for fine-tuned control

• Mix voice types — use a preset for one character, a designed voice for another, and a cloned voice for the narrator

Save Voices to the Picker

Designed voices, cloned voices, and strong speaker performances can be saved to your personal voice picker. This lets you reuse the same narrator or character voice in later projects without hunting through old audio.

You can also remove a saved voice from the picker without deleting the original media item from your library.

50+ Languages Supported

All three voice types support over 50 languages. Whether your story is in English, Japanese, Arabic, or Portuguese, you can generate natural-sounding speech.