Shona transcription: an honest view
Shona is a low-resource language for the speech model, with very little training audio. Expect a rough draft with many corrections. Slow, clear speech from one person close to the microphone gives the best draft; church services with music, busy markets and group calls will need much more fixing.
For a long interview, a rough draft is still quicker than typing from nothing. Click the line you want to check, listen, and correct it in place; edits save automatically.
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.
Spelling and word boundaries
Shona is written in the Latin alphabet with digraphs and clusters such as bh, dh, sv, zv, ny and mh. The model may misspell these or write words the way an English speaker would hear them.
Shona builds long words from prefixes and suffixes, and the draft may split one word into several or join words that should be separate. Fixing word boundaries is a common part of the review.
Dialects and English
Standard Shona draws on Zezuru, Karanga, Manyika and Korekore, and speakers from different regions sound different. Strong dialect or rural speech will need more correction.
Urban Shona mixes in a lot of English, from single words to whole sentences. Keep Shona selected when Shona dominates. If a meeting is mainly English, select English. Ndebele, the other large language in Zimbabwe, is not in the language list and will not transcribe properly as Shona.
What people record in Shona
Uploads include sermons and church events, research interviews for health and social studies, radio segments, and voice notes from family. Zimbabweans in South Africa, the UK and elsewhere use it to keep a written copy of conversations from home.
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 a recorded service or a YouTube interview, see the Shona video to text page.