An honest view of te reo Māori transcription
Te reo Māori is a low-resource language for the speech model: it saw very little Māori audio during training. Expect a rough draft with many corrections. Slow, clear speech from one speaker close to the microphone works best. Fast korero, karanga, waiata and recordings with several people at once will need far more work.
Even a rough draft can save time on a long recording, because you correct lines while listening instead of typing every word. Click a line to replay it and fix it in place; changes save as you go.
Upload the recording as it is: MP3, M4A, WAV, OGG, OPUS, FLAC or AAC, a voice note saved from WhatsApp or Telegram, or a video file such as MP4 or MOV. You can also record from your microphone in the browser. Long files are split and processed in parallel, so a ten-minute recording usually takes a minute or two.
Macrons and spelling
Written Māori marks long vowels with macrons: ā, ē, ī, ō, ū. The transcript may leave macrons out or place them inconsistently, and vowel length changes meaning. Check macrons on every line you plan to publish.
The alphabet is small, with the digraphs ng and wh, and words are built from open syllables, which helps when you correct by ear. Personal names, iwi and hapū names, and place names are the most common errors, so keep a list handy while reviewing.
Dialects and English in the same recording
Iwi have their own pronunciation and vocabulary. In the south, for example, Kāi Tahu often use k where other dialects use ng, and the model tends to write the more common form. Fix these to match the speaker.
Many recordings move between te reo and New Zealand English. If a hui or interview is mostly English with Māori greetings and phrases, select English for that file; Māori words will then need checking. Keep Maori selected when most of the speech is in te reo.
What people record in te reo
Uploads include interviews with kaumātua for whānau and iwi archives, whaikōrero recorded at hui, te reo lessons and practice sessions, iwi radio segments, and research interviews. Language learners use the draft to follow along and check what they heard.
Exports and next steps
Export TXT or DOCX for notes and documents, PDF for a fixed copy, SRT or VTT for subtitles, and CSV with one row per line and its start time. Timestamps and speaker names can be switched on or off in each export. Speaker labels are available on paid plans or with a Minute Pack.
For video, such as kapa haka performances or recorded hui posted online, see the Maori video to text page.