Back to Models
AudioMITOpen source weights and code

Whisper Large V3

OpenAI · Whisper

Open speech recognition model commonly used for transcription and multilingual audio workflows.

Best for

Builders adding local transcription, podcast processing, meeting notes, or audio translation.

Tradeoffs

Not an LLM chat model; accuracy and speed depend on language, audio quality, and runtime.

Local hardware notes

Can run locally; GPU improves throughput for batch transcription.

Local workflow notes

Commonly used for local transcription workflows; GPU improves batch throughput.

Local runtimes: Transformers, faster-whisper, whisper.cpp

Platforms: Windows, macOS, Linux

Hardware10GBRuntimeTransformers, faster-whisper, whisper.cppContextAudio segment basedUpdated2026
OpenAI Whisper model card