Whisper large-v3

OpenAI's open-weights multilingual speech recognition models; large-v3-turbo is a faster, smaller variant.

Where it ranks

A
Transcription
Models · Local · 4.1% on Artificial Analysis Speech to Text: AA-WER v2 (non-streaming)

Vendor: OpenAI
Family: Whisper
Released: 6 Nov 2023
Weights: Open: download and run it yourself
License: Apache-2.0
Parameters: 1.54B
GPU memory to run locally: ~10 GB (OpenAI README: the large model needs ~10 GB of VRAM (turbo ~6 GB); quantized ports such as whisper.cpp need less.)
API price: $0.0011 per minute of audio (Artificial Analysis lists $1.15 per 1,000 minutes (Whisper Large v3, provider fal.ai); divided by 1,000.)
Access: Free (open weights)
Last verified: 18 Oct 2026

Price from artificialanalysis.ai, 18 Oct 2026.

Benchmark	Result	Entry on the leaderboard	As of	Source
Artificial Analysis Speech to Text: AA-WER v2 (non-streaming)	4.1%	`Whisper Large v3` AA-WER v2 (non-streaming), provider fal.ai; embedded value 0.0407 converted to percent and rounded; page shows no last-updated date.	18 Oct 2026	artificialanalysis.ai
Coval Benchmarks: Speech-to-Text WER (24h window)	4.4%	`baseten / whisper-large-v3` Coval STT benchmark, mean WER over the trailing 24h window (snapshot generation 2610, as_of 2026-10-19T09:38Z), n=456 clips; rank 16 of 31; read from the public API that feeds https://benchmarks.coval.ai.	19 Oct 2026	benchmarks-api-6wxgp27p2a-ue.a.run.app
Hugging Face Open ASR Leaderboard (English, short-form average WER)	7.2%	`openai/whisper-large-v3` Average WER over the board's default datasets (English short-form, version 17-10-2026); rank 38; read from the Space's initial table data.	17 Oct 2026	huggingface.co