You can design a New Zealand AI voice with one prompt
Describe the accent, gender, age and delivery in one sentence and Gradium returns a New Zealand voice id you call from the API or the SDK. Every New Zealand voice is built to order, so the age, gender and delivery are yours to specify rather than picked from a shelf.
Kiwi accent, NZ English, New Zealander accent and new zealand all describe the same voice. Write it as New Zealand English in your prompt.
Hear it
- 0:00
“Take a breath. I need your full name and your date of birth before we go any further.”
The prompt
that produced it
A New Zealand female voice, 25 to 35: mid pitch, steady natural pacing, medium energy and an easy unforced resonance. Accent detail: centralised KIT, raised DRESS and TRAP, non-rhotic, terminal rise. Ideal for natural dialogue and voice agents.
A worked example: change any part of it and the voice changes with it. The four styles below show what moving pitch, pace, energy or purpose does to the same accent.
- Pitch1/5
- lowhigh
- Pace2/5
- slowfast
- Energy2/5
- calmboisterous
New Zealand
in four styles
A prompt is built from parts: the accent, the age, then pitch, pace, energy and what the voice is for. Change one part and you get a variation. These four are starting points to adapt, not finished prompts.
Everything to the middle. Watch KIT centralisation: it is the feature a mid-range read is most likely to soften, and the one a listener places New Zealand by.
A New Zealand English male voice, 30 to 45: easy and unforced, with mid pitch, steady natural pacing, medium energy and a natural unforced resonance. Ideal for voice agents, assistants and dialogue that has to sound unscripted.
In colour: the 9 parts that make this style.
Pitch, pace and energy drop together. Moving one alone produces a voice performing gravity rather than carrying it, and in New Zealand it usually costs kit centralisation.
A New Zealand English male voice, 45 to 60: clean, deliberate and precise, with low pitch, slow pacing, low energy and deep resonant timbre. Ideal for audiobooks, documentary and long-form narration.
In colour: the 9 parts that make this style.
Warmth belongs in the resonance rather than the energy. Keep an ear on DRESS and TRAP raising, which a support brief tends to flatten.
A New Zealand English male voice, 35 to 50, for customer service: calm and crisp, with mid-low pitch, steady natural pacing, medium energy and warm rounded resonance. Ideal for reassuring walkthroughs and empathic de-escalation.
In colour: the 10 parts that make this style.
Check this by ear before committing. How much energy an accent carries before it reads as theatrical varies sharply, and New Zealand is no exception: push it and listen for whether kit centralisation survives.
A New Zealand English male voice, 25 to 35: bright and punchy, with mid-high pitch, fast pacing, high energy and bright forward resonance. Ideal for advertising reads and social video.
In colour: the 9 parts that make this style.
What makes New Zealand
sound like itself
Each feature below is something the prompt has to encode, or something a careless prompt will accidentally undo.
- KIT centralisation
- The vowel in kit centralises towards a schwa, so fish and chips leans towards fush and chups. This is the single feature that separates New Zealand from Australian, and it is the first thing to listen for when auditioning.
- DRESS and TRAP raising
- Dress raises towards kit and trap towards dress, so pen approaches pin and bad approaches bed. The whole front vowel system shifts up, which is why the accent can be mistaken for Australian by ear until kit gives it away.
- Non-rhotic
- Post-vocalic r is dropped, as in Australian and Standard British. Anchoring the prompt to an American reference for any other quality will pull the r back in.
- High rising terminal
- Statements frequently end on a rise, as in Australian, which reads as friendly and open. It suits conversational and hospitality work with very little prompt effort.
Design your own custom New Zealand voice
for your use case
Voice Design generates New Zealand voices to order, so you specify the age, gender and delivery you need rather than choosing from a shelf. This is the difference between a voice library and a voice model: a library can only offer you what it already holds, while Voice Design builds the accent on request.
The prompt,
and where it goes wrong
The method behind the prompt: what each clause does, what breaks it, and what it was tested on.
Each row is one part of the prompt above and what it is set to here. Change a single row and you get a variation on this voice; change several and you get a different one.
| Clause | This prompt |
|---|---|
| Accent / localechanged | New Zealand English |
| Gender | male |
| Age range | 55 to 65 |
| Character | clean, deliberate and precise |
| Pitch | low pitch |
| Pace | slow pacing |
| Energy | low-to-mid energy |
| Resonance / timbre | resonant timbre |
| Modifiers | a gentle low-to-high flow |
| Applications | projecting academic authority |
2 failure modes we hit repeatedly, and what fixes each one.
- Auditioning without kit, fish or six words leaves the accent easily mistaken for Australian, since centralised KIT is the main separator.
- Put those vowels in the line. It is the single test that distinguishes the two accents by ear.
- Anchoring to an American reference reintroduces the r and undoes the non-rhotic base.
- Keep references inside the accent and describe qualities directly.
Descriptor words do not transfer between languages. Energetic and bright travel intact, but most resolve to a different sound depending on the language they are read in, so a brief that produced a warm voice in one language will not produce the equivalent warmth translated into another. Write it in English terms rather than translating one that worked elsewhere.
Writing your first prompt? How to write a voice prompt covers every part a prompt can carry, and what each one changes.
Questions?
Answered
A New Zealand English male voice, 55 to 65: clean, deliberate and precise, with low pitch, slow pacing, low-to-mid energy, resonant timbre and a gentle low-to-high flow. Ideal for projecting academic authority. Name the accent as New Zealand English, then set the age, the pitch, the pace, the energy and what the voice is for. Every accent Gradium maps is reached the same way.
KIT centralisation above all: The vowel in kit centralises towards a schwa, so fish and chips leans towards fush and chups. This is the single feature that separates New Zealand from Australian, and it is the first thing to listen for when auditioning.
Describe it and Voice Design builds it. Voice Design generates New Zealand voices to order, so you specify the age, gender and delivery you need rather than choosing from a shelf. One prompt returns a voice id you can call from the API straight away.
Those are names for the same territory, and this page covers them. New Zealand English is the wording Gradium maps, so that is what to name in the prompt, but a brief written in any of these terms lands in the same place.
Both. Gender is its own part of the prompt, so it changes on its own: swap male for female and everything else holds. Same accent, same age, same delivery, different voice.
Yes. A designed voice is generated rather than cloned from a person, so there is no actor to license and no session to re-book when the script changes.
Hear New Zealand
in the studio
Every voice we ship clears blind listener comparison and an ELO ranking first, because roughly one candidate in a thousand has it. For New Zealand, the feature that decides it is usually KIT centralisation.
Paste the prompt, change the parts that matter to you, and generate. No recording, no casting, no licensing.