Short instructions
Step lists, setup guides, and safety notes, the use our note names. One step per line, a pause tag before each action.
Yuwen, short Mandarin instructions, one step per line
Our note on Yuwen is one line, short Mandarin instructions, and no recipe we kept includes her, so this page has less listening behind it than Ruoxi's or Weilun's. What it has is the record, a D grade with C target quality and 10 to 100 minutes of training audio, and the mechanics that matter for instructions: pauses, readings, and captions.
ChineseFemaleDSentence-level captionsStandard voice
Hear it
Three samples, three registers
- A slow harbour line; listen for whether an instruction voice keeps its steps-and-pauses shape on a descriptive sentence.
- The hook with a three-hour saving in it; listen for how the numbers land, since instructions are full of quantities.
- A personal letter line; listen for whether the aside after the comma is set apart clearly.
On the record
Instructions, and the pauses that make them followable
An instruction script lives on its pauses. The engine gives about four tenths of a second at a comma or full stop, and a pause tag inserts more where a viewer needs time to act. Captions are cut at those same pauses, so one step per line gives one cue per step.
Readings matter more here than in narration: 行 as a table row, 长 as length, 重 as again. The engine takes the most frequent reading, so run Tidy up script or add the Pronounce as tag for any step that depends on the right one.
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
Instructions, checklists, and app walkthroughs
App walkthroughs
Menu names and buttons read exactly as written. English labels inside the Mandarin are read as English automatically.
A second voice for tutorials
Not yet listened to in any blend; the pairings below are where we would start.
Blends
Pairings to try under an instruction read
Nothing here is a kept recipe. Each card is a pairing we would try first; Yuwen keeps the pronunciation and the second voice lends timbre.
RuoxiChinese
With Ruoxi
A pairing to try, two Mandarin females. Ruoxi is the base of six kept recipes, so her timbre is the best documented in the set.
50% Ruoxi
MayaEnglish (US)
With Maya
A pairing to try. Clear Mandarin with Ruoxi kept Maya at 80 percent; listen for whether the same share lifts an instruction read.
80% Maya
NellEnglish (UK)
With Nell
A pairing to try. Instructional Mandarin with Ruoxi kept Nell at 90 percent; Yuwen in front of the same partner is the obvious next test.
90% Nell
JiahaoChinese
With Jiahao
A pairing to try, two Mandarin voices with tutorial notes: Jiahao reads brief tutorial steps by our note.
50% Jiahao
Blend Yuwen with any second voice
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
Yuwen on the published list
| Language | Chinese |
|---|---|
| Voice | Female |
| 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
Questions about Yuwen
How do I add a pause before each step?
Insert a pause tag at the start of the line, or end the previous line with a full stop for the engine's own pause. Longer pauses are cut into the audio as real silence.
Will the captions match my step list?
One step per line gives one cue per step, anchored to the pause between them and cut at 16 characters a line. Mandarin voices report no per-word timing, so the cues are sentence-level.
Can Yuwen read the English in a mixed script?
Yes. Text is split by writing system before synthesis, so app names and button labels in Latin letters are read as English inside the Mandarin.
Why are there no kept recipes on this page?
We only list blends we listened to and kept, and none starts from Yuwen yet. The widget lets you try the pairings above, free and without signing in.
Similar voices
Other Chinese voices to compare
Generate with Yuwen
Paste a script, keep Yuwen or blend a second voice, and download the MP3 with subtitles.