# OpenAI: Whisper Large V3

> OpenAI's open speech recognition model. Transcribes audio in around 100 languages and is billed per second of audio.

- Model ID: `openai/whisper-large-v3`
- Maker: OpenAI (`openai`)
- Context length: -
- Input: audio
- Output: transcription
- Capabilities: -
- Page: https://tokenlane.de/models/openai/whisper-large-v3

## Providers

| Providers | Data centers | Sovereign EU | Zero data retention |
|---|---|---|---|
| OVHcloud | FR | yes | yes |
| IONOS | DE | yes | yes |
| Scaleway | FR | yes | no |
| TensorX | IE, FI | no | yes |

## Usage

- Base URL: `https://api.tokenlane.de/v1` (OpenAI- and OpenRouter-compatible)
- Authentication: `Authorization: Bearer $TOKENLANE_API_KEY`
- Guide: https://tokenlane.de/docs/guides/audio.md?lang=en
- Machine-readable catalogue: `GET https://api.tokenlane.de/v1/models?output_modalities=all` (public, no key)
- Documentation index for agents: https://tokenlane.de/llms.txt

_Catalogue snapshot: 2026-11-19T13:10:34.963Z_
