Kannada speech-to-text
PoorWe sent 30 Kannada 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% | 30% | 0 of 30 | 0 of 30 | 0.143× real time |
Poor. Good for topic and keywords. Not good enough to read as a transcript. 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 | ಅದರೂ, ಪ್ರಾಧಿಕಾರಗಳಿಂದ ಸಲಹೆ ಪಡೆಯಿರಿ, ಎಲ್ಲ ಚಿಹ್ನೆಗಳಿಗೆ ಬದ್ಧರಾಗಿ ಮತ್ತು ಸುರಕ್ಷತೆ ಎಚ್ಚರಿಕೆಗಳ ಬಗ್ಗೆ ಹೆಚ್ಚು ಗಮನ ಹರಿಸಿ. |
| Whisper Large v3 | ಆದರು ಪ್ರಾದಿಕಾರವಿಂದು ಸಲಹೆ ಪಡೆರಿ ಎಲ್ಲಾ ಚಿನ್ನವಿಳಿ ಬತ್ತರಾಗಿ ಮತ್ತು ಸುರಕ್ಷತೆ ಎಚ್ಚರಿಕಿವಳಪಕ್ಕೆ ಹೆಚ್ಚು ಗಮನಾರಿಸಿ. |
Language detection
All 10 clips we sent without a language field were identified as Kannada. Auto-detection is safe here; sending language=kn still skips the detection step.
What to do instead
We would rather you know this before you build than after. For Kannada, 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 Kannada from Hugging Face run on your own hardware. If your audio mixes Kannada 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 Kannada?
On 30 clean read-speech clips it made 70% word errors. Good for topic and keywords. Not good enough to read as a transcript. Real recordings with noise, accents or several speakers will score worse.
Does language auto-detection work for Kannada?
In our test, yes: all 10 clips sent without a language were identified as Kannada. Sending language=kn still saves the detection step on every request.
Can it translate Kannada speech to English?
The API returns Kannada 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: Telugu (70%) · Tamil (73%) · Malayalam (over 100%)