Long narration
Articles, chapters, and documentary scripts, where our note about holding a long read matters most.
Maya, the grade A American English narration voice
Maya holds the only A on the published voice list, and she is the voice the engine's own examples use. Our own listening note reads: warm and even, holds a long read without drifting. That is why she is our first pick for narration.
English (US)FemaleAWord-level captionsStandard voice
Hear it
Three samples, three registers
- Listen for whether the pace stays even across the long clause.
- Listen for how she handles urgency.
- Listen for warmth in a personal register.
On the record
What a grade A on the published list means
Maya is the only voice graded A on the published list, which does not print her target-quality or training-hours fields; the grade stands alone.
Our listening note adds: warm rather than bright, an even tone, no drift over a long read, and accurate pronunciation with a little natural intonation.
Length the engine likes. The published guidance puts the sweet spot at roughly 100 to 200 tokens, a few sentences; very short lines are the weak spot and very long ones can rush.
Where we would use it
Long narration first, then anything that needs an even read
Courses and explainers
Scripts with technical terms and numbers, where pronunciation is the point. Try 0.9 times for learners.
The clean half of a blend
In the recipes we kept, Maya is the second voice in Clear Mandarin, Clear Mandarin male, and Clear French.
Blends
Recipes we kept with Maya as the base
Recipes we listened to and kept because we liked the result; our taste, not a ranking. Maya keeps the pronunciation in each.
DelaneyEnglish (US)
With Delaney
Audiobook narrator, an even split. Our note on Delaney is a lower, throatier delivery; listen for Maya's diction with more body.
50% Delaney
WalterEnglish (US)
With Walter
Warm narrator at 70 percent Walter, or 30 in the brighter version. Listen for how much of Walter you want under Maya.
30% to 70% Walter
GrantEnglish (US)
With Grant
Neutral duo, an even split with our neutral American male. Listen for a voice that reads as neither female nor male.
50% Grant
BrookeEnglish (US)
With Brooke
Clean explainer at 90 percent Brooke, or 80 in the variant. Listen for Brooke's character over Maya's pronunciation.
80% to 90% Brooke
Recipes we kept with Maya
Clean explainer
Brooke's character with Maya's accuracy.
Maya 10% + Brooke 90%
Clean explainer · more Maya
Same character, a little more tone.
Maya 20% + Brooke 80%
Audiobook narrator
Even and warm with husk underneath; holds a long read.
Maya 50% + Delaney 50%
Neutral duo
Half clear female, half neutral male.
Maya 50% + Grant 50%
7 more in the generator
Blend Maya with any second voice
A fixed sample at this mix, rendered once and cached. No credits used.
Every blend works the same way: the first voice sets the pronunciation and pacing, the second voice lends only its timbre, and you choose the ratio between 10 and 90 percent. See the three steps on the voice library page
At a glance
Maya on the published list
| Language | English (US) |
|---|---|
| Voice | Female |
| Overall grade | A |
| Target quality | Not published |
| Training audio | Not published |
| Captions | Word-level captions |
| Cost | 1 credit per job, room for 10,000 characters |
| Formats | MP3 free, WAV on paid plans |
| Commercial use | Included on every plan |
| Preview | Free, no sign-up |
Grade, target quality, and training audio come from the engine's published voice list and estimate training data, not how a voice sounds.
FAQ
Questions about Maya
What does Maya's A grade mean?
It is the grade in the engine's published voice list, an estimate of the quality and quantity of her training audio. Maya is the only voice with an A.
Can Maya read Japanese or Chinese text?
No. Chinese and Japanese characters are outside her reading model. Use a Mandarin or Japanese primary and blend Maya in second.
Is Maya free to use in a published video?
Yes. Standard voice output is licensed for commercial use on the free plan, with no attribution and no watermark on the download.
Do I get word-level subtitles with Maya?
Yes. English voices report every word's timing during synthesis, so the SRT and VTT cues change on the spoken word.
Similar voices
Other English (US) voices to compare
Generate with Maya
Paste a script, keep Maya or blend a second voice, and download the MP3 with subtitles.