Sundanese transcription: an honest view
Sundanese is a low-resource language for the speech model, even though it has tens of millions of speakers in West Java. Expect a rough draft with many corrections. The draft also tends to drift into Indonesian words and spelling, because the model knows Indonesian much better. Slow, clear speech from one person works best.
A rough draft still saves typing on a long file. Click a line to hear it again and fix it in place.
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 speech levels
The transcript uses the Latin alphabet. Sundanese has vowels that Indonesian lacks, written é and eu, and these are the first things to check: the draft often writes e or drops the eu. Aksara Sunda, the traditional script, is not produced.
Sundanese has speech levels, the polite lemes register and the everyday loma register, with different words for the same thing. The model does not handle the distinction well, so polite forms in a formal speech may come out as everyday words or as Indonesian.
Sundanese and Indonesian
Most Sundanese speakers switch between Sundanese and Indonesian, sometimes inside a sentence. Auto-detect usually picks Indonesian, which is why this page sets Sundanese. If a recording is mostly Indonesian with some Sundanese phrases, select Indonesian for that file instead, since the model handles Indonesian much better.
What people record in Sundanese
Uploads include pengajian and religious talks, interviews for local research and journalism, wayang golek and other performances, radio segments, vlogs, and family voice messages. Students use it for interviews with older speakers in Bandung, Bogor and villages across West Java and Banten.
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 YouTube vlog or a recorded performance, see the Sundanese video to text page.