{"schema":"postcutoff/model@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/m/whisper-large-v3/","md":"https://postcutoff.com/m/whisper-large-v3/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"whisper-large-v3","name":"Whisper large-v3 / large-v3-turbo (open weights)","org":"OpenAI","family":"Whisper","released":"2023-11-06","status":"legacy","type":"audio/speech","modality_in":["audio"],"modality_out":["text"],"open_weights":true,"model_license":"mit","context_window":null,"max_output":null,"knowledge_cutoff":null,"pricing":null,"price_line":"Price not published","access":[{"provider":"Hugging Face","model_id":"openai/whisper-large-v3","url":"https://huggingface.co/openai/whisper-large-v3"},{"provider":"Hugging Face","model_id":"openai/whisper-large-v3-turbo","url":"https://huggingface.co/openai/whisper-large-v3-turbo"},{"provider":"GitHub","url":"https://github.com/openai/whisper"},{"provider":"Groq","model_id":"whisper-large-v3-turbo","docs":"https://console.groq.com/docs/speech-to-text"},{"provider":"Deepgram (hosted)","model_id":"whisper-large","docs":"https://developers.deepgram.com/docs/models-languages-overview"}],"capabilities":[{"name":"Robust multilingual ASR + translation to English","detail":"99 languages; timestamps; zero-shot speech translation into English; the de facto open ASR baseline.","first":false,"discovered":"launch","source":"https://huggingface.co/openai/whisper-large-v3"},{"name":"Turbo: 4-layer decoder","detail":"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.","first":false,"discovered":"launch","source":"https://huggingface.co/openai/whisper-large-v3-turbo"}],"entry":null,"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.","verified":"2026-09-29","body_md":"Sources: https://huggingface.co/openai/whisper-large-v3-turbo , https://github.com/openai/whisper","page_url":"https://postcutoff.com/m/whisper-large-v3/","standing":{"kind":"speech and audio","newer_count":107,"newer":[{"id":"nemotron-3-5-transcribe","name":"NVIDIA Nemotron 3.5 Transcribe (30B-A4B)","org":"NVIDIA","released":"2026-10-28","page_url":"https://postcutoff.com/m/nemotron-3-5-transcribe/"},{"id":"hy-simulmt-30b-a3b","name":"Hy-SimulMT-30B-A3B","org":"Tencent","released":"2026-10-22","page_url":"https://postcutoff.com/m/hy-simulmt-30b-a3b/"},{"id":"eleven-realtime-v1-max","name":"Eleven Realtime v1 Max / Mini","org":"ElevenLabs","released":"2026-10-20","page_url":"https://postcutoff.com/m/eleven-realtime-v1-max/"},{"id":"voxtral-mini-transcribe-3","name":"Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3)","org":"Mistral AI","released":"2026-10-20","page_url":"https://postcutoff.com/m/voxtral-mini-transcribe-3/"},{"id":"voxtral-small-transcribe-3","name":"Voxtral Small Transcribe 3","org":"Mistral AI","released":"2026-10-20","page_url":"https://postcutoff.com/m/voxtral-small-transcribe-3/"}],"before":{"id":"whisper-1","name":"Whisper (whisper-1 API)","org":"OpenAI","released":"2023-03-01","page_url":"https://postcutoff.com/m/whisper-1/"},"after":{"id":"gpt-4o-transcribe","name":"GPT-4o Transcribe / Mini Transcribe / Transcribe Diarize","org":"OpenAI","released":"2025-03-20","page_url":"https://postcutoff.com/m/gpt-4o-transcribe/"},"weights":"public","licence":"mit","licence_permissive":true,"summary":"Weights are public under a permissive licence (MIT)."}}