Skip to content
Scriptorium
Transcribe free

Samples

Indonesian speech to text: a real sample transcript

What the free preview returns for a short Indonesian recording (Bahasa Indonesia), with the audio, the sources and the mistakes left in.

Updated

Indonesian (Bahasa Indonesia), 27 seconds, taken 2026-10-27. Sentences read aloud by a volunteer. Output of the free preview with the language set to Indonesian, not corrected.

CC0 1.0

The transcript, as the engine returned it

  1. Dia akan menjadi doktor dalam 2 tahun.
  2. Apakah disini sering hujan saat musim panas?
  3. Aku sudah tidak terhan lagi.
  4. Memberi lebih baik daripada diberi.
  5. Saya ingin mengunjungi Viji.
  6. Tujuan aku ingin mempelajari bahasamu.

Download this transcript as SRT (written by the same exporter the app uses; the other formats are TXT, timestamped TXT, VTT, Markdown, JSON and CSV).

Against the reference sentences

Word error rate 20.0% (7 edits over 35 words), character error rate 3.8%; normalisation: plain (explained on the samples page).

The sentences the speaker was asked to read:

  1. Dia akan menjadi doktor dalam dua tahun.
  2. Apakah di sini sering hujan saat musim panas?
  3. Aku sudah tidak tahan lagi!
  4. Memberi lebih baik daripada diberi.
  5. Saya ingin mengunjungi Fiji.
  6. tujuan aku ingin mempelajari bahasa mu
In the reference sentenceIn the transcript
dua2
di(missing)
sinidisini
tahanterhan
fijiviji
bahasa(missing)
mubahasamu

Where the recording comes from

  • Source: Mozilla Common Voice 22.0, test split (CC0 1.0 public domain dedication, https://commonvoice.mozilla.org/en/datasets, https://creativecommons.org/publicdomain/zero/1.0/; copy used: https://huggingface.co/datasets/fsicoli/common_voice_22_0, whose card also says cc0-1.0).
  • Licence: CC0 1.0 (creativecommons.org/publicdomain/zero/1.0/).
  • Which recording: One volunteer speaker (male, twenties): the speaker with the most clips in the part of the test archive we read, their clips in the test file's order that are 2.5 to 7 seconds long and have no down-votes, until about 24 seconds were collected. Chosen by that rule, not by how well the engine did.
  • Clip ids: common_voice_id_20953540, common_voice_id_20953586, common_voice_id_20953588, common_voice_id_20953591, common_voice_id_20953631, common_voice_id_20953633.

How every sample was made, step by step, is on the samples page. To try your own Indonesian recording, use the Indonesian transcription page.

Questions

What did the engine get wrong in this Indonesian clip?
5 words were substituted, 2 were missing and 0 were extra, out of 35 reference words. For example: dua became 2; di became (missing); sini became disini.
Can I use the Indonesian recording?
CC0 1.0. The source is named above.

Try it with your own file

Upload a recording and read the transcript.

Transcribe free — no sign-up Create free account