Telugu speech-to-text
Not usableWe sent 30 Telugu test clips through this API. Whisper Large v3 made 70% word errors, which is not good enough to read as a transcript. This page shows what came back so you can judge for yourself.
Measured accuracy
| Model | Word error rate | Character error rate | Clips with no errors | Empty transcripts | Speed |
|---|---|---|---|---|---|
Whisper Large v3openai/whisper-large-v3 | 70% | 34% | 0 of 30 | 0 of 30 | 0.158× real time |
Not usable. Most words come out wrong. Do not build on it for this language. 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 | ఇరాక్ పట్ల కార్యనిర్వాహక వర్గం యొక్క ప్రస్తుత విధానం యొక్క దాదాపు ప్రతి అంశాన్ని ఈ నివేదిక తీవ్రంగా విమర్శిస్తుంది మరియు ఇది తక్షణం దిశను మార్చాలని కోరుకుంది. |
| Whisper Large v3 | ఇరాక్ పట్లా కార్యనిర్వాహక వర్గం యక్క ప్రస్తుత విదానం యక్క దాదాపు ప్రతి అంసాన్ని ఇనివేదిక తేవరంగా విమర్షిస్తుంది మరియు ఇ |
Language detection
Send language=te. Of 10 clips sent without it, 9 were identified as Telugu; the others were labelled Malayalam (1). 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 Telugu, 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 Telugu from Hugging Face run on your own hardware. If your audio mixes Telugu 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 Telugu?
On 30 clean read-speech clips it made 70% word 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 Telugu?
Mostly. Of 10 clips sent without a language, 9 were identified as Telugu; the rest were labelled Malayalam (1). A wrong label means the transcript is written in the wrong language, so always send language=te.
Can it translate Telugu speech to English?
The API returns Telugu 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: Kannada (70%) · Tamil (73%) · Malayalam (over 100%)