Skip to content

Whisper large-v3-turbo

Hugging Face (open weights) Open weights

The catch: A little less accurate than large-v3: the card says the speed comes at the expense of a minor quality degradation.

AccessOpen weights
Free limitsFree to download and self-host; you pay only for your own compute. 809M speech-recognition model: Whisper large-v3 with the decoder cut from 32 to 4 layers, so it is much faster. MIT licence.
Modalityaudio
Credit cardNot required
Commercial useAllowed
Trains on your data–
Licence or termsMIT
Context window–
Model idopenai/whisper-large-v3-turbo
Base URL–
Last checked8 Oct 2026

How to use Whisper large-v3-turbo

Download the weights and serve them yourself; the quickstart below shows one way. Licence: MIT.

Quickstart
pip install -U transformers accelerate && python -c "from transformers import pipeline; print(pipeline('automatic-speech-recognition', model='openai/whisper-large-v3-turbo')('audio.mp3')['text'])"
Paste into Claude Code
I want to run the open-weight model "Whisper large-v3-turbo" (openai/whisper-large-v3-turbo) for my project.
Please:
1. Check the model card and tell me the hardware it needs and the simplest way to serve it (vLLM, SGLang, Ollama or a hosted endpoint).
2. Give me a minimal working setup and a test request.
3. Tell me the licence terms for commercial use.
4. If a cheaper or smaller variant would do the job, mention it.

Before you ship on it

  • A little less accurate than large-v3: the card says the speed comes at the expense of a minor quality degradation.
  • MIT (licence tag on the HF repo): use, modify and sell freely; keep the copyright notice.
  • Free to run means you pay for the GPUs, the serving stack and the on-call.

Questions

Is Whisper large-v3-turbo free?

Yes. Open weights offers it as open weights, with these limits: Self-host free · MIT. No credit card is needed.

Can I use Whisper large-v3-turbo commercially?

Yes, under MIT. Check the current terms before you ship.

How do I start with Whisper large-v3-turbo?

Download the weights and serve them yourself; the quickstart below shows one way. Licence: MIT.

Source: huggingface.co/openai/whisper-large-v3-turbo, checked 8 Oct 2026.