Whisper Large V3
OpenAI's Whisper Large V 3 is a state-of-the-art audio model for automatic speech recognition and speech translation, trained on over 5 million hours of labeled data. It is genuinely best at generalizing to many datasets and domains in a zero-shot setting, demonstrating improved performance over a wide variety of languages with a 10% to 20% reduction of errors compared to its predecessor.
Input
Output
Context
0K
Max Output
2K
Parameters
1.5B
Technical Specifications
Model TypeAudio
Context Window1 tokens
Max Output Tokens1,500 tokens
Parameters1.5B
Release DateNov 7, 2023
Training CutoffNot available
Licenseapache-2.0
Open SourceYes
Input Modalities
Audio
Output Modalities
Text
Capabilities
Resources & Links
Estimated GPU Requirements for Whisper Large V3
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 23, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.