Sinhala video to text, step by step
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.
After processing, the transcript sits next to a player. Click a line to play from there, correct it, and the change is saved straight away.
Spoken Sinhala, written Sinhala and English
Sinhala is strongly diglossic: news readers and formal speeches use literary forms, while vlogs and teledramas use everyday spoken Sinhala. The draft follows what is said, so expect spoken forms in casual videos and a mix where a speaker switches register.
Sri Lankan speakers drop English words into almost every sentence, from class and exam to software terms. Those words may appear in English letters or spelled out in Sinhala script. Pick one style while editing if the text will be published.
What people transcribe in Sinhala
Common uploads:
- Online tuition and A/L class recordings, for revision notes.
- Bana sermons and dharma talks, to share as text.
- YouTube news segments and political speeches, for quotes.
- Teledrama scenes and vlogs, for subtitles.
- Family videos sent home by Sri Lankans in the Middle East, Italy or Australia.
Sinhala subtitles
Export SRT or VTT after correcting the draft. The files are UTF-8; YouTube displays Sinhala correctly, but some desktop editors and older players render the vowel signs and conjuncts in the wrong place. A Unicode font with full Sinhala support, such as Noto Sans Sinhala, fixes most of these problems. Text pasted in from older legacy-font documents may look right but be stored as Latin characters, so keep the transcript in Unicode. DOCX and PDF keep the script for printing.
Accuracy and the audio page
Sinhala has limited training data, so expect a draft that needs real editing: long words broken in odd places, names misspelled and some words missed. Clear speech from one person gives the best result; classroom echo, crowd noise and music cut it further. Speaker labels are available on paid plans and with a Minute Pack.
The transcript stays in Sinhala; 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. For audio-only recordings, see the Sinhala audio to text page.