Inference APIs

Measured accuracy

ModelWord error rateCharacter error rateClips with no errorsEmpty transcriptsSpeed
Whisper Large v3
openai/whisper-large-v3
over 100%over 100%0 of 304 of 300.117× real time

Not usable. Most words come out wrong. Do not build on it for this language. Most Lao clips came back written in Thai script, which is why the character error rate is near 100% even where the words were recognised. 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.

Spokenອຳນາດການປົກຄອງສູນກາງຂອງໂບດໄດ້ຢູ່ກຸງໂຣມເປັນເວລາຫລາຍພັນປີແລ້ວ ແລະ ການເປັນຈຸດສຸ່ມອຳນາດ ແລະ ເງິນໄດ້ເຮັດໃຫ້ຫລາຍໆຄົນຕັ້ງຄຳຖາມວ່າທິດສະດີນີ້ຖືກຄົ້ນພົບ ຫຼຶ ບໍ່.
Whisper Large v3อำนาจการปกครองศูนย์ก่างของบด ได้อยู่กรุงโรมเป็นเวลาหลายพันปีแล้วและการเป็นจุดสุมอำนาจและเงินได้เห็ดให้หลาย ๆ คนตั้งคำถามว่า ทิศดีนี้ คือ คนโพบหรือ บ่

Language detection

Send language=lo. Of 10 clips sent without it, only 6 were identified as Lao; the others were labelled Thai (4). When detection is wrong, Whisper writes the transcript in the language it guessed.

What to do instead

We would rather you know this before you build than after. For Lao, look at services that train specifically on the language, such as Google Cloud Speech-to-Text or Azure AI Speech, both of which publish their language lists, or a Whisper checkpoint fine-tuned on Lao from Hugging Face run on your own hardware. If your audio mixes Lao with a well-supported language, the well-supported parts will still transcribe. You can confirm all of this on your own audio with the free credit on a new account: transcription playground.

FAQ

How accurate is Whisper for Lao?

On 30 clean read-speech clips it made over 100% character errors. Most words come out wrong. Do not build on it for this language. Real recordings with noise, accents or several speakers will score worse.

Does language auto-detection work for Lao?

Not reliably. Of 10 clips sent without a language, 6 were identified as Lao; the rest were labelled Thai (4). A wrong label means the transcript is written in the wrong language, so always send language=lo.

Can it translate Lao speech to English?

The API returns Lao text. For English, transcribe first and translate the text with a chat model on the same key; with accuracy this low the translation will inherit the errors.

Related languages: Thai (12%) · Khmer (100%)