Instructional scripts
Setup guides and procedures, the use our note names. One action per line, a pause tag where the viewer needs time.

Instructional scripts are the use our note gives Meera. Her published record is the Hindi standard, a C grade with B target quality and 10 to 100 minutes of training audio, and like the other Hindi voices she returns word-level timing, which matters for step-by-step captions.
Hear it
On the record
An instructional script is a list of actions with numbers in it, and Hindi is the one non-English set here where the caption can follow each word. One step per line gives one cue per step, and the word timing inside the cue lets a viewer see exactly where the voice is.
The grade is the shared Hindi line, tens of minutes at B target quality, a fact about the training data rather than the read. The samples above are the evidence for the read; the second one, a hook with numbers, is closest to an instruction.
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
Setup guides and procedures, the use our note names. One action per line, a pause tag where the viewer needs time.
Highlight each word as it is spoken in the SRT, useful for viewers following along on a phone.
Ananya, Rohan, and Arjun can sit behind her; the pairings below start there.
Blends
Nothing here is a kept recipe. Each card is a pairing to try; Meera keeps the Hindi pronunciation and the second voice lends timbre.
A pairing to try, two Hindi voices: Ananya reads lesson introductions by our note.
50% Ananya
A pairing to try. Harper is our English software-tutorial voice; listen for a tutorial timbre on Hindi steps.
50% Harper
A pairing to try, the Hindi male our note assigns to product demonstrations.
40% Arjun
A pairing to try. Grant is our neutral American male for walkthroughs; listen for whether 50 percent of him steadies a step list.
50% Grant
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 | Hindi |
|---|---|
| Voice | Female |
| Overall grade | C |
| Target quality | B |
| Training audio | 10 to 100 minutes |
| Captions | Word-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
One action per line, plus a pause tag where the cursor moves; the SRT then has one cue per line with word timing inside it.
Each was trained on 10 to 100 minutes of audio at B target quality, and the set totals one to ten hours. The grade measures that, not the sound.
Write them in Devanagari if you want them read the Hindi way; the Pronounce as tag lets you spell out any name.
Yes. Standard voices carry commercial rights on every plan, with no watermark and nothing to credit.
Similar voices
Paste a script, keep Meera or blend a second voice, and download the MP3 with subtitles.