Hausa results: what to expect
Hausa is spoken by tens of millions of people, but the speech model has seen very little of it. Expect a rough draft with many corrections. It works best on slow, clear speech from one person close to the microphone, such as a teacher, a preacher or a single interviewee. Noisy market recordings, phone calls and group conversations will need heavy editing.
The draft is still a starting point: timed lines to correct are usually quicker than typing a long recording by ear.
Upload the recording as it is: MP3, M4A, WAV, OGG, OPUS, FLAC, a voice message or a phone recording. You can also record from your microphone in the upload box. Nothing needs converting first.
Boko spelling and hooked letters
The transcript uses Boko, the Latin-script spelling used in Nigerian and Nigerien schools and media. Points to check during review:
- The hooked letters ɓ, ɗ and ƙ and the glottalised ƴ (also written 'y) may come out as plain b, d, k and y.
- Tone and vowel length are not written in standard Hausa spelling, so words that differ only in tone can be confused.
- Ajami, the Arabic-script spelling of Hausa, is not available as output.
- Names, especially Arabic-origin names, may be spelled in more than one way.
English and Arabic in Hausa speech
Hausa in Kano, Kaduna, Abuja and Niamey mixes in English (in Nigeria) or French (in Niger), and religious speech uses many Arabic words and Qur'anic quotations. Borrowed words may be written as they sound in Hausa spelling. Keep Hausa selected when most of the recording is Hausa; for a mostly English recording with Hausa phrases, choose English.
Auto-detect is unreliable for Hausa and may guess another language entirely, so set it yourself, as this page does.
The transcript opens next to a player that highlights the current line. Click a line to hear it again, correct the word in place, and your changes save automatically.
What people transcribe in Hausa
Common recordings are Islamic lectures and tafsir, radio programmes, interviews for NGO and health research in northern Nigeria and Niger, voice messages from family, and Kannywood film dialogue. Researchers often have a fluent speaker correct the draft before translating it.
Export TXT, DOCX, PDF, CSV, SRT or VTT, with timestamps and speaker names switched on or off per export. Speaker labels are available on paid plans or with a Minute Pack.
For video files, see the Hausa video to text page.