Short instructional explainers
One concept in a minute or two for a UK audience, the use our note names.

The published list puts Nell at D: target quality C, training audio between 10 and 100 minutes. Our note gives her short instructional explainers. She is the second voice in one recipe we kept, Instructional Mandarin, at 90 percent under Ruoxi, which we kept for its tone.
Hear it
On the record
C-quality audio measured in minutes gives the D that Nell shares with Freya among the British female voices. The published list grades training data and notes that sound is subjective.
Our note keeps her on short explainers. The kept recipe borrows her instructional colour under a Mandarin primary, which says the timbre transfers; Ruoxi keeps the pronunciation.
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
One concept in a minute or two for a UK audience, the use our note names.
Ruoxi leading with 90 percent Nell, for Mandarin instructions with a British colour.
Multi-part explainers render as one file with one subtitle track.
Blends
The kept recipe puts Nell second. With Nell leading, these are pairings to try; the pronunciation stays British.
Imogen is our top-graded British voice at B-; listen for whether 60 percent of her steadies an explainer.
60% Imogen
Freya is our British lesson-script pick at the same D; listen for two lesson voices together.
50% Freya
Grant is our neutral American male; listen for a neutral body under British pronunciation.
50% Grant
Our note on Delaney is low and throaty; listen for whether half of her warms the read.
50% Delaney
Mandarin with a British instructional tone.
Ruoxi 10% + Nell 90%
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 (UK) |
|---|---|
| Voice | Female |
| 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 timbre transfers and pronunciation does not. Ruoxi says every Mandarin syllable; Nell's 90 percent share adds an instructional colour we liked.
The published list estimates training data: C-quality audio in the 10 to 100 minute band. Play the samples; the list calls sound subjective.
A sentence or two per line. The published guidance names very short and very long utterances as the weak spots.
Yes. English voices, British included, report word timing during synthesis, so the SRT cues follow the read.
Similar voices
Paste a script, keep Nell or blend a second voice, and download the MP3 with subtitles.