Somali transcription: what to expect
Somali is a low-resource language for the speech model. Expect a rough draft with many corrections, especially in names, places and fast speech. One clear speaker close to the microphone gives the best draft. Noisy phone calls, community meetings where people talk over each other, and recordings with music will need much more work.
Even so, correcting a draft while you listen is usually faster than typing a long interview. Click a line to replay it, fix it, and the change is saved.
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.
Somali spelling
Somali uses the Latin alphabet adopted in 1972, where c and x stand for sounds English does not have, and long vowels are written double (aa, ee, ii, oo, uu). Check these closely:
- Long and short vowels, which the draft often mixes up.
- The letters c, x, kh, dh and q, which may be swapped or dropped.
- The apostrophe for the glottal stop, as in ba'an, which may be missing.
- Arabic religious phrases, which may be spelled in different ways.
Dialects and code-switching
The model is closest to standard northern Somali, used in most media. Speakers of Maay, common in southern Somalia, sound very different and will get a much weaker draft. Speakers from Djibouti, the Somali Region of Ethiopia and northern Kenya may also need more corrections.
Somali conversation abroad mixes in English, Swedish, Norwegian and other local languages, plus Arabic in religious contexts. Keep Somali selected when Somali dominates; if a meeting is mainly in English, select English for that file.
What people record in Somali
Uploads include interviews for research and community health projects, journalism, religious lectures, poetry, radio segments, and voice messages from family. Somali communities in Minneapolis, Columbus, London, Toronto and Scandinavian cities use it to keep a written copy of meetings and calls.
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 YouTube lecture or a TikTok clip, see the Somali video to text page.