Report summaries
Briefings and digests read straight, the use our note names.

Marcus is a D on the published voice list: C-quality reference audio, 10 to 100 minutes of it. Our note gives him narrated report summaries. He is the second voice in one recipe we kept, Mandarin report, at 70 percent under Zhiyuan, a pairing we liked rather than a measure of anything.
Hear it
On the record
C-quality audio in the 10 to 100 minute band is the record behind the D, shared with Dean, Miles, and Caleb. Grades describe training data; the list itself calls sound subjective.
Our note keeps him on summaries, factual prose read plainly. We also kept him under a Mandarin primary, which shows that his timbre transfers across languages while Zhiyuan keeps every syllable.
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
Briefings and digests read straight, the use our note names.
Zhiyuan leading with 70 percent Marcus, for report reads in Mandarin with a male timbre.
Announcements and updates that should not sound performed.
Blends
The one kept recipe puts Marcus second, under a Mandarin voice. With Marcus leading, these are pairings to try.
Chloe is our article-summary pick, graded C+; listen for a two-voice briefing.
50% Chloe
Grant is our neutral American male at C+; listen for whether he steadies a D-graded read.
60% Grant
Our note on Delaney is low and throaty; listen for whether half of her warms a summary.
50% Delaney
Maya is warm and even by our note; listen for whether 60 percent of her carries a longer report.
60% Maya
Report-summary read, two male voices.
Zhiyuan 30% + Marcus 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 | Male |
| Overall grade | D |
| Target quality | C |
| Training audio | 10 to 100 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
Because a second voice lends timbre and never changes pronunciation. Zhiyuan says every Mandarin syllable; Marcus adds a male timbre at 70 percent. We kept it because we liked it.
It is the published estimate of training data, C-quality audio in the 10 to 100 minute band, and nothing more.
Yes. No cap; one credit gives a job room for 10,000 characters of English, one continuous file, one subtitle track.
Yes. Standard voice output carries commercial rights on every plan, with no watermark.
Similar voices
Paste a script, keep Marcus or blend a second voice, and download the MP3 with subtitles.