How to run Distil-Whisper large-v3 locally

Hugging Face · Speech → text · 760M params · MIT (commercial OK)

A knowledge-distilled Whisper large-v3 that is ~6x faster and half the size as a near drop-in English ASR replacement.

What it costs to run — $0 markup

On your own machine — $0. Runs free if you have about 5.0 GB of VRAM (fp16 ~5GB; English-focused, ~6x faster than large-v3), via faster-whisper / Transformers.
Rent a GPU — from $0.26/hr. Fits RTX 3090 24GB at the direct vendor price ($0 markup) — pay only for the minutes you generate.
Download the weights — free. Open weights at distil-whisper/distil-large-v3.

Note: generative-media models are billed per image / per second / per minute on hosted services — not per token. Running locally or on your own rented GPU is usually far cheaper and keeps your data on your machine.

Key facts

Does	Speech → text
VRAM to run	~5.0 GB (fp16 ~5GB; English-focused, ~6x faster than large-v3)
Download	~1.5 GB
Parameters	760M
License	MIT (commercial use OK)
Run with	faster-whisper / Transformers

Get Distil-Whisper large-v3 on Hugging Face →

More voice & audio models

Whisper large-v3 — Speech → text, ~10 GB VRAM
Whisper large-v3-turbo — Speech → text, ~6.0 GB VRAM
Kokoro-82M — Text → speech, ~1.0 GB VRAM
XTTS-v2 — Voice cloning, ~6.0 GB VRAM
MusicGen Large — Text → music, ~16 GB VRAM
Chatterbox — Text → speech, ~8.0 GB VRAM

Browse: all media models · chat / LLM models