Whisper Large V3 Turbo

OpenAI

4.5x faster than Whisper Large V3 with minimal quality loss. Decoder reduced from 32 to 4 layers. Most-downloaded Whisper variant (4.6M+ monthly). Best speed/accuracy balance for local STT.

Speech-to-Text Local Latest Whisper Family vv3-turbo
Type
Speech-to-Text
Source
Local
License
MIT

Whisper Family 2 models

The full Whisper line by generation — pricing and capabilities vary across the family.

Whisper
Large V3 Turbo Current Latest
Speech-to-text, transcription, translation
Oct 2024
Large v3 Latest
Speech-to-text
-

Capabilities

🌊
Streaming

Local Model Specs

Architecture
Transformer Encoder-Decoder (4-layer decoder)
Runtime
faster-whisper / whisper.cpp
Disk Size
1.6 GB

Details

Release Date
October 1, 2024
Knowledge Cutoff
-
Source
Local
License
MIT
Model ID
whisper-large-v3-turbo-local
Last updated: March 13, 2026