Story excerpts
Short fiction, picture-book text, and chapter openings, the use our note names. One sentence per line gives one caption per sentence.

Yukiko is a Japanese voice whose training source the published list spells out: a reading of ごん狐, Gon the Fox, the children's story by Niimi Nankichi. That is 10 to 100 minutes of audio at B target quality, a C grade, and it fits our note exactly: story excerpts.
Hear it
On the record
The list gives her source as Gon the Fox, a story read aloud, so the audio she learned from is narration with dialogue and description in it. Our note gives her story excerpts. None of that says how she sounds; the samples do.
She also sits behind a recipe we kept, Mandarin with a Japanese tone: Ruoxi reads the Mandarin and Yukiko at 90 percent supplies the timbre. It is the clearest demonstration that a second voice changes the sound and not the words.
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
Short fiction, picture-book text, and chapter openings, the use our note names. One sentence per line gives one caption per sentence.
A page read aloud to judge a longer project. The speed slider goes down to half speed with the pitch unchanged.
Mandarin with a Japanese tone is the recipe we kept with her behind Ruoxi. The same move works from any primary.
Blends
Yukiko's kept recipe puts her second. The cards below put her first; each is a pairing to try, with Yukiko reading every character.
Reverse of the kept recipe: Yukiko in front, Ruoxi behind; the kept version runs the other way.
50% Ruoxi
A pairing to try, two Japanese voices; Sakura has the most training audio on the list and a note for clean readings.
50% Sakura
A pairing to try. Delaney supplies the husky edge in both kept Japanese recipes; listen for it under a story.
60% Delaney
A pairing to try. Rosalind is our British book-excerpt voice; listen for a book timbre on Japanese narration.
50% Rosalind
Mandarin pronunciation with a Japanese timbre.
Ruoxi 10% + Yukiko 90%
A fixed sample at this mix, rendered once and cached. No credits used.
A cross-language blend: Yukiko 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 | Japanese |
|---|---|
| Voice | Female |
| Overall grade | C |
| Target quality | B |
| 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
The published list names the recording she learned from: a reading of Niimi Nankichi's story, 10 to 100 minutes of audio. A fact about the data, not a promise about the tone.
Yes. Nothing caps the length. Billing counts bytes, so a credit carries about 3,300 characters in one job, and the cost is shown first.
The engine takes the most common reading. For a rarer one, wrap the word in the Pronounce as tag with the kana, or let Tidy up script add the tag where it is confident.
Standard voice output carries commercial rights on every plan, with no watermark and no attribution line.
Similar voices
Paste a script, keep Yukiko or blend a second voice, and download the MP3 with subtitles.