All models

Whisper

by OpenAI

Transcription

Whisper is OpenAI's speech-to-text model, transcribing audio across many languages with strong robustness to accents and background noise. The large-v3 and faster large-v3-turbo variants suit everything from meeting notes to media captioning.

Publisher
OpenAI
Licence
MIT
Model card on Hugging Face

Run Whisper

Install it on a Pendra worker, then call it through the OpenAI-compatible API with a pdr_sk_ key.

from pendra import Pendra

client = Pendra(api_key="pdr_sk_...")

with open("meeting.mp3", "rb") as f:
    result = client.audio.transcriptions.create(
        model="whisper-large-v3-turbo",
        file=f,
    )

print(result.text)

Run Whisper on your own UK infrastructure

Deploy a worker, install Whisper, and start serving it through one sovereign API endpoint.

Related models