Getting a Somali video transcribed
Drop in the video file without converting it: MP4, MOV, MKV, WEBM, AVI, 3GP or a screen recording from your phone. The audio is pulled out on our server, so every timestamp still points to the right moment in the video. If the video is online, choose Import from link and paste a public link from YouTube, TikTok, Vimeo, Dropbox or Google Drive, or a direct link to the file; only the sound is downloaded.
Videos shared on WhatsApp or Facebook can be saved to the phone and uploaded. The draft opens beside a player; click a line to hear it again.
Somali spelling and what to expect
Somali is written in the Latin alphabet, with c for the sound ʿayn, x for a breathy h, and doubled vowels (aa, ee, oo) for long ones. The model often gets vowel length and these letters wrong, so a good share of the editing is putting back the right spelling.
Somali has little training data in the speech model. Expect a rough draft with many corrections, best on one clear speaker. Videos often mix in Arabic, especially religious talks with Quranic quotations, and English or Swedish in diaspora videos; those parts will be weaker still. Names of clans, towns and people are frequent errors, so keep a short list of the right spellings at hand and fix them line by line as you watch.
Somali videos people transcribe
Typical uploads:
- Religious lectures and khutbas posted on YouTube.
- News clips and interviews, for quotes.
- Poetry and storytelling videos, to keep as text.
- Family videos and community meetings filmed in Minnesota, London, Sweden or Nairobi.
Subtitles and documents
Export SRT or VTT to add Somali subtitles on YouTube or in a video editor. Correct the draft first, because the subtitle file is built from your edited text. DOCX and PDF suit community records and reports, and TXT pastes into a message. CSV gives one row per line with its start time, which helps if you are indexing a long lecture so others can jump to a topic. Speaker labels for interviews and meetings are available on paid plans and with a Minute Pack.
English and the audio page
The transcript stays in Somali; there is no built-in translation. To read it in English, open the Google Translate link on the transcript, or use the AI prompt export to hand the text to ChatGPT, Claude or Gemini. Machine translation of Somali is also weaker than for major languages, so have a Somali speaker check anything important. For audio-only recordings, see the Somali audio to text page.