Free New Zealand English Speech-to-Text
Upload your New Zealand English audio or video and get an accurate, editable transcript in minutes — automatic, browser-based and free to start.
New Zealand English is spoken by around 5 million people and is one of the more distinctive varieties of English, best known for its shifted short vowels — the sound changes that turn 'fish and chips' into the famous 'fush and chups'. It is the everyday language of Aotearoa's news, business, classrooms and creators.
ConvertSpeech transcribes it automatically. Upload your audio or video and our speech-recognition engine writes out the spoken English with punctuation, ready to copy into a document, subtitle file or translation tool. It runs in your browser, needs no installation, and your first minutes are free with no account required.
What people transcribe New Zealand English for
Journalists and interviews
Turn recorded New Zealand interviews into quotable text in minutes instead of hours.
Researchers and students
Convert lectures and interviews into searchable notes you can quote and analyse.
Creators and media
Generate subtitles and show notes straight from your video or podcast audio.
How ConvertSpeech handles New Zealand English
The Kiwi accent is defined by its vowels: the short 'i' is centralised (so 'fish' can sound like 'fush'), 'e' raises towards 'i', and 'a' shifts towards 'e'. New Zealand English also draws heavily on te reo Māori, with everyday loanwords such as 'kia ora' (hello), 'whānau' (family), 'kai' (food) and 'marae' appearing naturally in speech.
ConvertSpeech is trained on a broad range of English accents and handles New Zealand speakers well from clear recordings. Common Māori loanwords are increasingly recognised, though less common words and place names transcribe more reliably when the audio is clean. As always, the largest factor in accuracy is recording quality — a clear signal with little background noise beats everything else.
Tips for accurate New Zealand English transcription
- Record with a good microphone and minimal background noise for the best accuracy.
- Keep the language set to English rather than auto-detect when you know the recording is English.
- One speaker at a time transcribes best; overlapping speech reduces accuracy.
- Review Māori words and place names after transcription, as spelling can vary in the output.
- For interviews, enable speaker detection (a free registered feature) to label each speaker.