Sinhala transcription: an honest view
Sinhala is a low-resource language for the speech model. Expect a rough draft with many corrections. One clear speaker in a quiet room gives the best result; calls, teledrama clips with music and group conversations will need a lot more editing.
Review is quicker than typing. Play the file, follow the highlighted line, and click any line to hear it again before you correct it.
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.
Sinhala script and spoken forms
The transcript is in Sinhala script. Check vowel signs, the aspirated and unaspirated consonant pairs, and the prenasalised letters such as ඬ and ඳ, which the draft often confuses.
Sinhala has a wide gap between spoken and literary language. The model mostly writes what was said, so a casual interview produces colloquial forms. If you need formal written Sinhala for a report, plan to rewrite rather than just correct.
English and Tamil in Sinhala recordings
Sinhala speakers, especially in Colombo, mix in many English words, and the transcript may write them in Sinhala script or in Latin letters. Keep Sinhala selected when Sinhala dominates; choose English for meetings that are mostly in English.
Tamil is the other main language of Sri Lanka. A recording that switches between Sinhala and Tamil will be weaker in whichever language is not selected, so pick the one most of the recording uses.
What people record in Sinhala
Uploads include Buddhist sermons (bana), interviews for research and journalism, lectures and tuition classes, radio segments, and voice messages from family. Sri Lankans working or studying in the Middle East, Italy, South Korea, Australia and the UK use it for calls with relatives.
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 sermon or a teledrama clip, see the Sinhala video to text page.