Yoruba transcription: an honest view
Yoruba is a low-resource language for the speech model. Expect a rough draft with many corrections. Slow, clear speech from one person close to the microphone gives the best result; owambe parties, church services with music and busy markets will need much more work.
For a long recording, correcting a draft is still quicker than typing from nothing. Click a line to replay it, fix it, and move on.
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.
Tone marks and underdots
Written Yoruba marks tone with accents (á, à) and uses underdotted letters ẹ, ọ and ṣ. The draft often leaves tone marks out, places them inconsistently or drops the underdots, and since tone changes meaning, a word can look right but be the wrong word. Decide whether your final text needs full tone marking and add it during review.
Names, places and Yoruba proverbs are the other common corrections. Proverbs (òwe) use compact, older wording that the model often mishears.
Yoruba, English and Pidgin
Most Yoruba speakers in Lagos and Ibadan switch freely into English and Nigerian Pidgin. Keep Yoruba selected when Yoruba dominates; if a recording is mainly English, select English and correct the Yoruba words by hand.
Regional varieties such as Ekiti, Ijesa or Oyo speech, and Yoruba from Benin and Togo, differ from the standard and will need more corrections.
What people record in Yoruba
Uploads include sermons and church events, research interviews, radio segments, Yoruba film dialogue, and family voice messages. Yoruba communities in the UK, the US and elsewhere use it to keep a written copy of conversations with parents and grandparents.
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 files, such as a Yoruba film clip or a YouTube sermon, see the Yoruba video to text page.