As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/whisper-large-v3/

# Whisper large-v3 / large-v3-turbo (open weights)

OpenAI, Whisper family. Status: legacy. Type: speech and audio. Released: 2023-11-06.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Hugging Face | `openai/whisper-large-v3` |  | https://huggingface.co/openai/whisper-large-v3 |
| Hugging Face | `openai/whisper-large-v3-turbo` |  | https://huggingface.co/openai/whisper-large-v3-turbo |
| GitHub |  |  | https://github.com/openai/whisper |
| Groq | `whisper-large-v3-turbo` |  | https://console.groq.com/docs/speech-to-text |
| Deepgram (hosted) | `whisper-large` |  | https://developers.deepgram.com/docs/models-languages-overview |

## Pricing

- Price not published.
- Last checked: 2026-09-29

## Specs

- Input: audio
- Output: text
- Context window: not published
- Max output: not published
- Open weights: yes
- Licence: mit

## Where it stands

- Newer speech and audio models in the registry since its release: 107. The 5 newest:
  - NVIDIA Nemotron 3.5 Transcribe (30B-A4B) (2026-10-28) https://postcutoff.com/m/nemotron-3-5-transcribe/
  - Hy-SimulMT-30B-A3B (2026-10-22) https://postcutoff.com/m/hy-simulmt-30b-a3b/
  - Eleven Realtime v1 Max / Mini (2026-10-20) https://postcutoff.com/m/eleven-realtime-v1-max/
  - Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3) (2026-10-20) https://postcutoff.com/m/voxtral-mini-transcribe-3/
  - Voxtral Small Transcribe 3 (2026-10-20) https://postcutoff.com/m/voxtral-small-transcribe-3/
- Before it from OpenAI: Whisper (whisper-1 API) (2023-03-01) https://postcutoff.com/m/whisper-1/
- After it from OpenAI: GPT-4o Transcribe / Mini Transcribe / Transcribe Diarize (2025-03-20) https://postcutoff.com/m/gpt-4o-transcribe/
- Weights are public under a permissive licence (MIT).

## What stands out

- Robust multilingual ASR + translation to English: 99 languages; timestamps; zero-shot speech translation into English; the de facto open ASR baseline. Source: https://huggingface.co/openai/whisper-large-v3
- Turbo: 4-layer decoder: large-v3-turbo (Oct 2024) prunes the decoder from 32 to 4 layers (809M vs 1.55B params) for much faster decoding with minor quality loss; not trained for translation. Source: https://huggingface.co/openai/whisper-large-v3-turbo

## Notes

Status legacy: still widely deployed, but surpassed on the Open ASR Leaderboard by NVIDIA Canary/Parakeet, and OpenAI's API now points to gpt-transcribe (whisper-1 API shutdown 2027-02-26). Known to hallucinate text on silence/noise. Dates from OpenAI releases (large-v3 at DevDay 2023-11-06; turbo 2024-10-01), not re-checked today.

Sources: https://huggingface.co/openai/whisper-large-v3-turbo , https://github.com/openai/whisper

Model page: https://postcutoff.com/m/whisper-large-v3/