Indonesian speech-to-text API: 5.5% word error, measured

Measured accuracy

Model	Word error rate	Character error rate	Clips with no errors	Empty transcripts	Speed
Whisper Large v3 `openai/whisper-large-v3`	5.5%	1.8%	17 of 30	0 of 30	0.053× real time

Excellent. Production quality. Transcripts can be used as they are for notes, search and subtitles. The clips are clean, single-speaker read speech, so treat this as a best case for your own recordings. How we measured, and all 83 languages.

What a transcript looks like

The clip with the median error rate from the test, reference text against what the API returned.

Spoken	Serupa halnya dengan itu, pria diharuskan memakai celana panjang yang menutup lutut.
Whisper Large v3	Serupa halnya dengan itu, pria diharuskan memakai celana panjang yang menutup lutut.

Language detection

Send language=id. Of 10 clips sent without it, only 5 were identified as Indonesian; the others were labelled Javanese (5). When detection is wrong, Whisper writes the transcript in the language it guessed.

Quickstart

The request is the OpenAI transcription request with a different base URL. language is optional in the API but, as shown above, not optional in practice for Indonesian.

cURL

curl https://api.inferenceapis.com/v1/audio/transcriptions \
  -H "Authorization: Bearer $INFERENCE_API_KEY" \
  -F "model=openai/whisper-large-v3" \
  -F "language=id" \
  -F "file=@recording.mp3" \
  -F "response_format=verbose_json"

Python · openai SDK

import os
from openai import OpenAI

client = OpenAI(base_url="https://api.inferenceapis.com/v1", api_key=os.environ["INFERENCE_API_KEY"])
with open("recording.mp3", "rb") as f:
    r = client.audio.transcriptions.create(model="openai/whisper-large-v3", file=f, language="id", response_format="verbose_json")
print(r.text)

Subtitles and timestamps

response_format=srt or vtt returns a subtitle file with cues of up to two lines, broken at sentence ends and pauses. verbose_json with timestamp_granularities[]=word returns a start and end time for every word if you want to build your own.

Cost

$0.002 per minute of audio on either model: $0.12 for an hour, $12 for a hundred hours. Duration is measured from the file you upload. There is no daily cap on minutes and no subscription; enough to run your own Indonesian test.

Notes for Indonesian

Indonesian, Malay (ms) and Javanese (jw) are easily confused by auto-detection, as the result above shows.

FAQ

How accurate is Whisper for Indonesian?

On 30 clean read-speech clips it made 5.5% word errors, about one word in 18. Production quality. Transcripts can be used as they are for notes, search and subtitles. Real recordings with noise, accents or several speakers will score worse.

Does language auto-detection work for Indonesian?

Not reliably. Of 10 clips sent without a language, 5 were identified as Indonesian; the rest were labelled Javanese (5). A wrong label means the transcript is written in the wrong language, so always send language=id.

Can it translate Indonesian speech to English?

The API returns Indonesian text. For English, transcribe first and translate the text with a chat model on the same key.

Related languages: Malay (8.6%) · Javanese (71%) · Tagalog (13%)