Speech to text

Whisper Large v3 API

Name: Whisper Large v3
Brand: OpenAI
SKU: whisper-large-v3

Whisper Large v3 speech-to-text on /v1/audio/transcriptions. One model, two runtimes: Vast GPU (large-v3-turbo) primary + AWS Lambda (tiny) fallback; the router selects per availability.

$0.004 / minute · read from the live catalogue

Whisper Large v3 costs $0.004 / minute on Open LLMs. Call it by sending whisper-large-v3 as the model id to /v1/audio/transcriptions, using any OpenAI-compatible client.

What are Whisper Large v3's specifications?

Every value here is read from the catalogue that serves the API, so this page and the service cannot disagree.

Model id: whisper-large-v3
Task: Speech to text
Price: $0.004 / minute
Modality: audio → text
Parameters: 809M
Licence: MIT
Endpoint: /v1/audio/transcriptions

How do I call Whisper Large v3?

Point an OpenAI client at our base URL and name the model. Nothing else about your request changes.

Whisper Large v3 — first requestbash

curl https://api.openllms.co/v1/audio/transcriptions \
  -H "Authorization: Bearer $OPENLLMS_API_KEY" \
  -F [email protected] \
  -F model=whisper-large-v3

Before your first call

An inference call needs an API key and a positive wallet balance. The first call to an idle model can answer 503 with a Retry-After header while it starts — wait, then retry. Full reference: the API docs.

How is Whisper Large v3 licensed?

Whisper Large v3 is served under the MIT licence. The upstream licence passes through to you: what you may do with the output is governed by it, not by us. The obligations we pass through are listed on model licences, and the model card itself is at its source.

What else can I call?

See every model in the catalogue with its price, context window and licence.