Game narration
Cutscene voiceover and quest text, the use our note names. Keep lines short so each cue lands on one beat.
Takeshi, the only Japanese male on the list, a slower cadence for game narration
Takeshi is the only male among the five Japanese voices, and his record is short: under ten minutes of training audio, a reading of 蜘蛛の糸, The Spider's Thread by Akutagawa Ryunosuke, at B target quality, which makes him a C-. Our note is a listening note: a slower cadence, suited to game narration.
JapaneseMaleC-Sentence-level captionsStandard voice
Hear it
Three samples, three registers
- Listen for the slower cadence our note describes on a descriptive line.
- Listen for whether a slow cadence can carry a hook, or whether the urgency is lost.
- Listen for the pause between the two sentences; a game line often needs that room.
On the record
One male voice, a slow cadence, a short record
The published list warns about his training duration, minutes and few of them, and grades accordingly. Our note is about pace rather than quality: slower cadence, and a use, game narration, where slower reads leave room for what is on screen.
The source named on the list is Akutagawa's short story, read aloud. That is what the voice learned from; it is not a description of how he sounds, and the three samples are.
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
Game narration, cutscenes, and slow reads
Slow, deliberate reads
Where a slower cadence is the point: warnings, endings, lines that need weight. The speed slider can slow him further.
The male half of a Japanese pair
Any of the four female Japanese voices can sit behind him; the pairings below start there.
Blends
Pairings to try around a slow male read
No recipe we kept includes Takeshi. Each card is a pairing to try; he keeps the readings and the cadence, the second voice lends its timbre.
SakuraJapanese
With Sakura
A pairing to try, the two Japanese voices with listening notes: clean readings behind a slower cadence.
50% Sakura
EdmundEnglish (UK)
With Edmund
A pairing to try. Edmund is our low British documentary voice; listen for whether 60 percent of him gives game narration more floor.
60% Edmund
DelaneyEnglish (US)
With Delaney
A pairing to try. Delaney's husky edge worked behind Sakura in two kept recipes; listen for it under a male read.
50% Delaney
YukikoJapanese
With Yukiko
A pairing to try, two story voices by our notes: Yukiko reads story excerpts.
50% Yukiko
Blend Takeshi 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
Takeshi on the published list
| Language | Japanese |
|---|---|
| Voice | Male |
| Overall grade | C- |
| Target quality | B |
| Training audio | Under 10 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 Takeshi
Is Takeshi the only male Japanese voice?
Yes, on the published list there is one male and four female Japanese voices. Blending lets a female voice or an English male lend him a different timbre.
What does slower cadence mean for timing?
It is our listening note, and it means more room per line. The subtitles are sentence-level either way, cut at real pauses and 16 characters a line.
Can I speed him up?
Yes. The speed slider goes above 1.0 as well as down to half speed, with the pitch unchanged.
Why C- with a B target quality?
Target quality B says the reference recording was reasonably clean; C- says there was very little of it, under ten minutes from The Spider's Thread.
Similar voices
Other Japanese voices to compare
Generate with Takeshi
Paste a script, keep Takeshi or blend a second voice, and download the MP3 with subtitles.