OpenAI logo

Whisper 3 Turbo


Whisper 3 Turbo is OpenAI logoOpenAI's speech to text model with a 4K context window and up to 4K output tokens. A turbo-speed third-generation Whisper ASR model designed for fast multilingual speech recognition with reduced latency.
Spec
Canonical IDopenai-whisper-3-turbo
TypeSpeech to Text
StatusActive
CreatorOpenAIOpenAI
Context Window4K tokens
Max Output4K tokens
Input ModalitiesAudio
Output ModalitiesText

Capabilities

Input1/5
Text·
Image·
Audio
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Whisper 3 Turbo4KCurrent
Whisper 34KAvailable
Whisper 3 Large$0.000$0.000Available
Whisper 3 Large Turbo$0.000$0.000Available
Whisper 2 LargeAvailable
Whisper$0.000$0.000Available
Whisper Base$0.000$0.000Available
Whisper Large$0.000$0.000Available
Whisper Medium$0.000$0.000Available
Whisper Small$0.000$0.000Available
Whisper Tiny$0.000$0.000Available

Model IDs