Product announcements
New features, pricing updates, and availability notices, the use our note names. Write the change as the first sentence.

Quinn is the one American voice on this site without a published grade: her engine voice is not in the published voice list, so there is no target quality or training figure to quote. What we have is our own note, short product announcements, and one recipe we kept, Product announcement, with 70 percent Quinn over Delaney's pronunciation.
Hear it
On the record
Nothing, officially. The published list covers 54 voices and hers is not among them; she ships with the engine build we run but was never graded, so we show that rather than guess a letter.
Our note gives her a narrow job: short product announcements. Product announcement is the one recipe we kept with her, and it uses her at 70 percent under Delaney because we liked the pairing. There is no grade to lean on.
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
New features, pricing updates, and availability notices, the use our note names. Write the change as the first sentence.
News-style vertical clips where a headline and two lines are the whole script.
Delaney leading with 70 percent Quinn. Start there, then adjust the share in the widget.
Blends
The one recipe we kept puts Quinn second, so these are pairings to try with Quinn leading. She keeps the pronunciation; the second voice lends timbre.
The reverse of Product announcement. Our note on Delaney is low and throaty; listen for whether half of her softens a notice.
50% Delaney
A pairing to try. Walter is our seasonal-announcement pick; listen for a public-address feel.
50% Walter
A pairing to try. Grant is our neutral American male; listen for a bulletin-like read.
50% Grant
A pairing to try for longer notices. Maya is our grade A narration voice; listen for whether 60 percent of her carries a minute of copy.
60% Maya
Short announcement read, lightly husky.
Delaney 30% + Quinn 70%
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 | Not in the published list |
| 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
Her engine voice is not in the published voice list, which is where every other grade on this site comes from. We would rather show that than invent one.
Our notes point Quinn at short product announcements and Sienna at hooks and promos. Sienna also carries an A- grade; Quinn has none. Listen to both samples on your own script.
In English the engine reads numbers and currencies as spoken. Symbols and units are spelled out by Tidy up script if you run it.
Yes. Word-level timing comes from the engine for every English voice, so the cues land on the spoken word.
Similar voices
Paste a script, keep Quinn or blend a second voice, and download the MP3 with subtitles.