Spoken updates
Weekly notes, progress logs, and letters read aloud, the use our note names.

Jules is graded D on the published voice list: a C target quality and 10 to 100 minutes of training audio. Our note gives her personal updates and spoken journal entries, first-person scripts rather than presentations. No recipe we kept includes her, so the pairings below are ones to try.
Hear it
On the record
A C target quality means the reference audio or its transcript was imperfect, and with minutes of audio the overall grade lands at D. The list is explicit that grades describe training data and that sound is subjective.
Our note is about register: personal updates, journal entries, the kind of script written in the first person. The third sample is exactly that kind of line, so it is the one to judge her on.
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
Weekly notes, progress logs, and letters read aloud, the use our note names.
First-person passages where a personal register matters more than polish.
Untested as a second voice; the widget on any profile lets you hear her under that voice.
Blends
None of these has been listened to. Jules keeps the pronunciation; the second voice lends timbre only.
Maya is our grade A narration voice; listen for whether 60 percent of her lifts a D-graded read without losing the personal tone.
60% Maya
Our note on Delaney is low and throaty; listen for a quieter, closer journal voice.
50% Delaney
Rory is our British story pick; listen for a story timbre under Jules's American pronunciation.
50% Rory
Brooke is our question-and-answer pick; listen for a more conversational update.
50% Brooke
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 (US) |
|---|---|
| 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
The grade describes training data, minutes of C-quality audio. The list says sound is subjective; play the third sample, which matches her noted use, and decide.
Yes. Blank lines already pause; a pause tag of up to five seconds sets an exact gap, and Tidy up script can place pauses for you.
Your text is kept only to render the job and is deleted with the audio when it expires, after 72 hours on the free plan. It is never used for training.
Yes. SRT and VTT files come with every job, timed word by word for English voices.
Similar voices
Paste a script, keep Jules or blend a second voice, and download the MP3 with subtitles.