Model Terminal

Whisper Large-v3-turbo

Whisper large-v3-turbo is OpenAI's speed-optimized multilingual speech recognition and translation model, derived from Whisper large-v3 by reducing the decoder from 32 layers to 4. It delivers faster transcription with a modest accuracy tradeoff, making it suitable for latency-sensitive ASR applications. Source: supabase.

Value score
Not scored
Context
tokens
Max output
tokens
Price

Capability radar

Peer value bars

Identity

Developer
Hugging Face
Openness
Modalities
Automatic-speech-recognition
Release
Knowledge cutoff
Deprecation
API docs

Benchmarks

No benchmark scores yet.

Compare nearby

Pricing

Input / 1M
Output / 1M
Speed