Skip to content
OpenAI

Whisper Large V3

flagship
OpenAI · released 2023-11-01 · text
currently routing · 4.2k rpm
1K tokens
Context
— / 1M
Input
— / 1M
Output
— t/s
Speed
proprietary
License
/ ABOUT

Whisper Large V3 is the latest and most capable version of OpenAI's Whisper speech recognition model, delivering improved accuracy across all supported languages. It features an enlarged vocabulary, better handling of accented speech, and reduced hallucination compared to earlier Whisper versions.

The model was trained on additional data with improved data filtering and augmentation techniques, addressing weaknesses in previous versions including better performance on low-resource languages, reduced timestamp errors, and fewer transcription hallucinations on silent or noisy audio.

Whisper Large V3 is recommended for all transcription applications requiring the highest accuracy, serving as the premium option in the Whisper model family.

Providers for Whisper Large V3

1 routes · sorted by uptime

ClosedRouter routes requests to the providers best able to handle your prompt size and parameters, with automatic fallbacks to maximize uptime.

Provider
Context
Quant
Uptime · 30d
bf16
0.00%