Whisper large-v3-turbo
Pilot $4,900 fixed
- Sizes
- 809M
- Active params
- All parameters (dense)
- Context
- 30 s windows
- Licence
- MIT
- Fits on
- CPU only at 4-bit, any GPU
- Endpoint
- llm.yourcompany.internal/v1
- Egress
- 0
- Owner
- YOU
Whisperon your own GPUs.
Whisper transcribes calls, meetings and voice notes on GPUs you control. The audio never leaves your network.
This card is the installation. Pick a size on its edge and it is re-issued.
The 72-hour pilot with Whisper.
$4,900 fixed. Whisper large-v3-turbo is the most downloaded of the two and fits on CPU only at 4-bit. The others fit on the same hardware or less.
Live on your data
72 h$4,900 fixed
Whisper live on your data in 72 hours. The clock starts after access and prerequisites.
Your endpoint
/v1OpenAI-compatible
OpenAI-compatible endpoint. Your applications switch by changing the base URL.
Your hardware
- Whisper large-v3-turboCPU only at 4-bit, any GPU
- Whisper large-v3CPU only at 4-bit, any GPU
The readout
Evalon your data
Reference evaluation on your data. Readout and production scoping.
We size the hardware and source it at cost, with no markup. Ballpark: one H100 80GB ≈ $25–30k; a 4×H100 node ≈ $180–240k; smaller models run on far less.
Same SDK. Change the base URL.
The model is one parameter. Everything else in your application stays as it is.
client = OpenAI(
base_url="https://llm.yourcompany.internal/v1", # inside your network
api_key="your-key",
)
text = client.audio.transcriptions.create(
model="whisper-large-v3-turbo",
file=open("call-2026-10-27.wav", "rb"),
)Licence, plainly.
- Whisper large-v3-turboMITCommercial use: permitted
- Whisper large-v3Apache 2.0Commercial use: permitted
Whisper large-v3-turbo is released under the MIT licence, which permits commercial use, modification and private deployment.
Whisper large-v3 is released under Apache 2.0: commercial use, modification and private deployment are permitted.
We read the current licence text against your use when we scope the pilot.
Published by OpenAI. We are not affiliated with the vendor. This is a summary, not legal advice.
Related models.
- VoxtralMistral AICPU only at 4-bitApache 2.0
- Gemma 4Google2 models, from 1× T4 16GB at 4-bitApache 2.0
- Qwen3AlibabaCPU only at 4-bitApache 2.0
Talk to an engineer.
Tell us the model, the data and the GPUs you have. An engineer from Limassol or Auckland scopes the 72-hour pilot with you.