How to run Moonshine (base) locally

Useful Sensors · Speech → text · 60M params · MIT (commercial OK)

An ultra-light streaming ASR family optimized for fast, accurate transcription on resource-constrained edge devices.

What it costs to run — $0 markup

On your own machine — $0. Runs free if you have about 2.0 GB of VRAM (Runs on CPU/edge; tiny footprint, beats Whisper-tiny), via Transformers / ONNX.
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 UsefulSensors/moonshine-base.

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	~2.0 GB (Runs on CPU/edge; tiny footprint, beats Whisper-tiny)
Download	~0.4 GB
Parameters	60M
License	MIT (commercial use OK)
Run with	Transformers / ONNX

Get Moonshine (base) 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