Calm explainers
Product walkthroughs and how-to scripts, the use our note names. Try 0.95 times.

Delaney is graded B- on the published list, with target quality B and 10 to 100 hours of training audio. Our notes call her delivery softer than the other American voices, low and throaty. She is the second voice in twenty of the thirty-five recipes we kept: our taste, not popularity.
Hear it
On the record
The list places her in the largest training band with a B target quality, the same footprint as Sienna and Imogen, and why she grades B- where most American voices grade C or D.
Our notes are about texture: a softer, lower delivery with a throaty edge. We kept blends with her under English, Japanese, Mandarin, and French primaries.
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
Product walkthroughs and how-to scripts, the use our note names. Try 0.95 times.
Twenty recipes we kept use her under another voice, Podcast host, Ad read, Magnetic Mandarin, and Husky Japanese among them.
Spoken letters, meditations, and updates where a bright voice would sound wrong.
Blends
All four below are recipes we listened to and kept; our picks, not a ranking. Delaney keeps her pronunciation as the primary.
Podcast host at 70 percent Maya, or an even split in the huskier version. Listen for Maya's diction over Delaney's delivery.
50% to 70% Maya
Q&A explainer at 70 percent Brooke, or 30 in the huskier version. Listen for which share keeps the read conversational.
30% or 70% Brooke
Product demo at 70 percent Miles, or an even split in the huskier version. Listen for a steadier walkthrough tone.
50% to 70% Miles
Ad read, an even split. Listen for whether it suits offers, trailers, and countdowns.
50% Walter
Question-and-answer clarity, lightly husky.
Delaney 30% + Brooke 70%
Same read with the throaty edge forward.
Delaney 70% + Brooke 30%
Crisp and close, with husk underneath.
Delaney 30% + Maya 70%
Even split; the throaty edge sits forward.
Delaney 50% + Maya 50%
16 more in the generator
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
| Language | English (US) |
|---|---|
| Voice | Female |
| Overall grade | B- |
| Target quality | B |
| Training audio | 10 to 100 hours |
| 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
The published list grades training audio: B target quality and a 10 to 100 hour band in her case. It does not grade timbre, which is what our notes describe.
Because we liked what her texture did under other voices. That is our preference, not demand.
No. The Mandarin primary decides every syllable; Delaney lends only timbre. Magnetic Mandarin is Meilin with Delaney at an even split.
Yes. Save up to eight blends in this browser from the generator's advanced settings.
Similar voices
Paste a script, keep Delaney or blend a second voice, and download the MP3 with subtitles.