---
title: "Whisper Large V3 Turbo API hosted in the EU"
description: "Transcribe audio with OpenAI's open Whisper Large V3 Turbo on inference.eu: the OpenAI transcription API format, with recordings processed in the EU."
canonical: "https://inference.eu/models/whisper-large-v3-turbo/"
language: "en"
---

Speech to text · OpenAI

# Run Whisper Large V3 Turbo in the EU through an OpenAI-compatible API

Whisper Large V3 Turbo is the faster version of OpenAI's open speech recognition model Whisper Large V3, released under the MIT licence. On inference.eu you call it with the same request format as OpenAI's transcription API, while your audio is processed in EU data centres and never used for training.

[Contact sales](https://inference.eu/contact/)[Example request](#example)

1.  01809M
2.  02EU data centres
3.  03MIT

## What Whisper Large V3 Turbo is

Whisper is OpenAI's family of open models for automatic speech recognition and speech translation. Large V3 Turbo, released in October 2024, is a pruned and fine-tuned version of Whisper Large V3: the same model, except that the number of decoder layers has been cut from 32 to 4. That makes it much faster, with about 809 million parameters in total.

It transcribes speech in the language spoken and can translate speech into English text. The model card lists 99 languages. Whisper processes audio in 30-second windows; longer recordings are transcribed by sliding over the audio in chunks, which the serving layer handles for you. The weights are released under the MIT licence.

## What it does well, and where it falls short

Whisper is the standard choice for turning recordings into text: meetings, interviews, voicemails, podcasts and support calls. It copes well with accents and background noise in the major European languages, adds punctuation, and can return timestamps for subtitles. The Turbo version keeps much of Large V3's accuracy while running far faster.

It only transcribes or translates; it does not summarise or answer questions about the audio. For that, use Voxtral Small or pass the transcript to a language model. Translation goes into English only. Accuracy is lower for languages with little training data, and like all speech models it can occasionally invent words in long silences or very noisy passages.

## Calling Whisper through the API

inference.eu supports the OpenAI transcription request format, so code that already uses OpenAI's speech-to-text API keeps working. Change the base URL to the inference.eu API, use your inference.eu key and set the model to `whisper-large-v3-turbo`.

Upload the audio file with an optional `language` hint, which improves accuracy and speed when you know the spoken language in advance. Ask for timestamps if you need subtitles or want to link text to positions in the recording. For translation into English, use the translation request instead of transcription. The OpenAI SDKs for Python and JavaScript support both out of the box.

## Recordings processed in the EU

Whisper was trained by OpenAI, but on inference.eu the open weights run on infrastructure in the European Union. Your audio files and transcripts are processed in EU data centres, are not sent to OpenAI, and are never used to train any model.

Every customer gets a data processing agreement under Article 28 of the GDPR and our subprocessor list, which matters for recordings that contain names, health details or customer information. Billing is in euros. The MIT licence allows commercial use without restriction. You remain responsible for telling people they are being recorded and for having a legal basis to do so.

## Whisper Large V3 Turbo

Maker

OpenAI

Made in

United States

Type

Speech to text

Parameters

809M

Licence

[MIT](https://opensource.org/license/mit)

Released

October 2024

Model ID

whisper-large-v3-turbo

Processing

EU data centres

Training on your data

Never

Source

[huggingface.co](https://huggingface.co/openai/whisper-large-v3-turbo)

whisper-large-v3-turbo · Python

```
import os
from openai import OpenAI

client = OpenAI(base_url="https://api.inference.eu/v1", api_key=os.environ["INFERENCE_EU_API_KEY"])

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

## What teams use it for

-   1

    ### Meeting and interview transcripts

    Turn recorded meetings, interviews and hearings into searchable text with timestamps.

-   2

    ### Subtitles for video

    Create timed subtitles for training videos, webinars and marketing content in the spoken language or in English.

-   3

    ### Call centre analytics

    Transcribe support calls in bulk, then pass the text to a language model for summaries, tagging and quality review.

## Whisper Large V3 Turbo: common questions

The questions buyers, developers and legal teams ask us most. Something missing? Ask us directly.

Compliance depends on how you handle recordings. On inference.eu, Whisper requests are processed in EU data centres, not used for training and covered by a data processing agreement under Article 28 GDPR with a published subprocessor list. Audio is not sent to OpenAI. You still need a legal basis for recording.

The model card lists 99 languages, including all major European languages such as German, French, Spanish, Italian, Dutch, Polish and Portuguese. Accuracy is highest for languages with plenty of training data. Passing the \`language\` parameter helps when you know the spoken language.

Turbo is a pruned version of Large V3 with the decoder reduced from 32 layers to 4, then fine-tuned. It runs much faster with a small loss in accuracy. For most transcription workloads Turbo is the practical choice.

Yes. Whisper Large V3 Turbo is released under the MIT licence, which allows commercial use, modification and redistribution with very few conditions. You can build it into paid products without an agreement with OpenAI.

No. OpenAI published the open weights, but it is not involved when you call Whisper on inference.eu. Your audio is processed in EU data centres, used only to produce your transcript and never used for training.

Whisper itself works on 30-second windows, and longer audio is transcribed chunk by chunk. That lets you send recordings of meetings or calls well beyond 30 seconds. For very large files, split them into parts before uploading to keep requests manageable.

Yes, into English. Whisper can transcribe speech in its original language or translate it directly into English text. It cannot translate into other target languages; for that, transcribe first and then translate the text with a model such as EuroLLM.

Yes. Whisper can return timestamps for segments of the transcript, which you can use to build subtitles or jump to the right place in a recording. Request them in the transcription call.

Whisper Large V3 Turbo is a small, fast model built only for transcription and translation into English. Voxtral Small is a 24B model that also understands what is said, so it can summarise and answer questions. Use Whisper for volume, Voxtral for understanding.

Change the base URL of your OpenAI client to the inference.eu API, use your inference.eu key and set the model to \`whisper-large-v3-turbo\`. The request and response format of the transcription call stay the same.

[Ask a question](https://inference.eu/contact/)

## Related

[All models](https://inference.eu/models/#directory)

-   [Voxtral Small 24BTranscribe and understand audio with Voxtral Small 24B from Mistral AI on inference.eu: an OpenAI-compatible API with processing in EU data centres.Speech to text](https://inference.eu/models/voxtral-small-24b/)
-   [gpt-oss-120bRun OpenAI's open-weight gpt-oss-120b reasoning model on inference.eu: the OpenAI API format, with requests processed in EU data centres, billed in euros.Reasoning](https://inference.eu/models/gpt-oss-120b/)
-   [multilingual-e5-large-instructRun multilingual-e5-large-instruct on inference.eu: compact embeddings in 100 languages for search, RAG and classification, processed in the EU.Embeddings](https://inference.eu/models/multilingual-e5-large-instruct/)

## Move your AI workloads to EU infrastructure

Tell us which models you use and roughly how much traffic you have. We reply within one working day with pricing and next steps.

-   Reply within one working day
-   Pricing for your volume
-   DPA ready to sign