How to run Canary 1B v2 locally

NVIDIA · Speech → text · 1B params · CC-BY-4.0 (commercial OK)

A commercially-licensed encoder-decoder model doing both transcription and speech translation across 25 European languages.

What it costs to run — $0 markup

On your own machine — $0. Runs free if you have about 6.0 GB of VRAM (~4-6GB; ASR + speech translation across 25 languages), via NVIDIA NeMo.
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 nvidia/canary-1b-v2.

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	~6.0 GB (~4-6GB; ASR + speech translation across 25 languages)
Download	~4 GB
Parameters	1B
License	CC-BY-4.0 (commercial use OK)
Run with	NVIDIA NeMo

Get Canary 1B v2 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