Announcements and offers
Seasonal promotions, event reminders, and countdowns, the use our note names. Write the offer as its own line.

Walter is one of four voices we ship with under ten minutes of training audio, and with a C target quality he carries the lowest grade of any, D-. Our note gives him one job, seasonal announcements, and we kept him as the second voice in three recipes, Ad read and both Warm narrator versions.
Hear it
On the record
The list is blunt about him: the training band under ten minutes carries a warning mark, and smaller durations pull the grade down.
Against that, our notes kept coming back to him for announcements and as a second voice under Maya and Delaney. Those are recipes we liked, not evidence of quality.
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
Seasonal promotions, event reminders, and countdowns, the use our note names. Write the offer as its own line.
Maya's pronunciation with 70 percent Walter, or 30 in the brighter version. Try it on audiobook chapters.
Delaney leading with an even split of Walter. Try it on offers and trailers.
Blends
Every recipe we kept uses Walter as the second voice, so these are pairings to try with Walter leading.
The reverse of Ad read, an even split with Delaney leading. Listen for Delaney's edge with Walter's words in front.
50% Delaney
The reverse of Warm narrator. Listen for whether 60 percent of Maya carries a long chapter over Walter's pronunciation.
60% Maya
A pairing to try. Sienna is brighter than Maya by our note; listen for whether half of her lifts an announcement.
50% Sienna
A pairing to try. Grant is our neutral American male; listen for a plainer read of the same announcement.
50% Grant
Announcer weight with a throaty edge.
Delaney 50% + Walter 50%
Male warmth with Maya's clean pronunciation.
Maya 30% + Walter 70%
Maya forward, a little male body.
Maya 70% + Walter 30%
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 | Male |
| Overall grade | D- |
| Target quality | C |
| Training audio | Under 10 minutes |
| 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 data, and Walter sits in the smallest band, under ten minutes, with a C target quality. D- is the lowest grade of any voice we ship.
Listen first. The list calls sound quality subjective, and we kept three recipes with him. Use full sentences; very short lines are the published weak spot.
Yes. Standard voice output is licensed for commercial use on every plan, with no watermark and no credit line.
Insert a pause tag of 0.4 to 0.8 seconds on the line before the offer, or let Tidy up script place pauses, then listen once at full speed.
Similar voices
Paste a script, keep Walter or blend a second voice, and download the MP3 with subtitles.