Report summaries
Quarterly notes, meeting recaps, and briefings, the use our note names. One finding per line keeps each caption cue to one point.

Zhiyuan is the Mandarin male our note assigns to brief report summaries, and the one recipe we kept with him is built for the same job: Mandarin report, with Marcus at 70 percent behind him, described in our note as a report-summary read from two male voices. His record is the standard Mandarin one, a D grade, C target quality, 10 to 100 minutes of audio.
Hear it
On the record
Report summaries are dense with numbers, dates, and names, and that is where Tidy up script matters most: the engine takes the most frequent reading, so 一行 in a table comes out xíng unless told háng.
Mandarin report keeps Zhiyuan at 30 percent and Marcus at 70. Marcus is our English report-summary voice, graded D as well; Zhiyuan's share sets the pronunciation and Marcus changes the weight.
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
Quarterly notes, meeting recaps, and briefings, the use our note names. One finding per line keeps each caption cue to one point.
Tables and totals read aloud. Run Tidy up script first so multi-reading characters such as 行 and 长 get the intended reading.
The kept recipe with Marcus for a heavier two-voice read. It is in the generator presets.
Blends
The Marcus card is a recipe we listened to and kept; the others are pairings to try. Zhiyuan sets the pronunciation in every case.
Mandarin report, kept at 70 percent Marcus: a report-summary read from two male voices, by our note. Our English report voice behind our Mandarin one.
70% Marcus
A pairing to try, two Mandarin males: Weilun is the base of five kept recipes, so his timbre is documented on his own page.
50% Weilun
A pairing to try. Our note on Edmund is low and British; listen for whether 60 percent of him gives a summary more floor.
60% Edmund
A pairing to try. Delaney is the throaty voice behind most of our Mandarin blends; listen for whether she suits a report.
50% Delaney
Report-summary read, two male voices.
Zhiyuan 30% + Marcus 70%
A fixed sample at this mix, rendered once and cached. No credits used.
A cross-language blend: Zhiyuan keeps the pronunciation, the second voice only lends its timbre.
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 | Chinese |
|---|---|
| Voice | Male |
| Overall grade | D |
| Target quality | C |
| Training audio | 10 to 100 minutes |
| Captions | Sentence-level captions |
| Cost | 1 credit per job, room for about 3,300 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
Sign in and run Tidy up script, which checks about fifty multi-reading characters against context, or wrap the word in the Pronounce as tag. The captions keep the original text.
Only the timbre. Zhiyuan at 30 percent still reads every character; Marcus at 70 percent adds his weight. Our note calls the result a report-summary read from two male voices.
Digits and most units read cleanly. Preview any figure that must be read a specific way and tag it with Pronounce as if needed.
Because Mandarin voices give no per-word timing; every cue sits on a real pause in the audio and lines are capped at 16 characters.
Similar voices
Paste a script, keep Zhiyuan or blend a second voice, and download the MP3 with subtitles.