Documentary openings
The setup minute before the footage takes over, the use our note names.

A C+ on the published list puts Warren among the three American male voices with an hour or more of B-quality audio. Our note gives him documentary introductions. No recipe we kept includes him, so the pairings below are ones to try.
Hear it
On the record
Among the American males only Warren, Grant, and Toby have an hour or more of B-quality audio, and all three grade C+. The rest are minutes of C-quality audio and grade D or D-.
Our note is specific: documentary introductions, the opening minute that sets up a subject. Grant's page carries the kept Documentary voice recipe; Warren is the untested alternative with the same grade.
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
The setup minute before the footage takes over, the use our note names.
How-something-works pieces of a few minutes, rendered as one file.
Same grade, different note: Grant is neutral, Warren is documentary. Play both first samples.
Blends
No kept recipe uses Warren. He keeps the pronunciation in each pairing; the second voice lends timbre only.
Documentary voice, the recipe we kept, pairs Grant with half Delaney; try Warren the same way and listen for depth.
50% Delaney
Our note on Edmund is a low British male for documentary voiceover; listen for a lower floor under American pronunciation.
50% Edmund
Maya is our grade A narration voice; listen for whether 60 percent of her softens an introduction.
60% Maya
Grant is our neutral American male at the same C+; listen for a plainer documentary read.
50% Grant
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 | C+ |
| Target quality | B |
| Training audio | 1 to 10 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
Grant has the kept recipe and a note that says neutral; Warren's note says documentary introductions. Both grade C+. Play the first sample of each.
No cap on length. A credit carries 10,000 characters of English, enough for a long read in one go, and the result is one continuous file.
Yes. A slow tag reads one phrase at a reduced rate, and the speed slider sets the overall pace from 0.5 to 2 times.
Yes. Standard voice output carries commercial rights on the free plan, without attribution.
Similar voices
Paste a script, keep Warren or blend a second voice, and download the MP3 with subtitles.