Moonshine

by Useful Sensors

Tiny English ASR optimized for resource-constrained devices.

TL;DR

Tiny English ASR optimized for resource-constrained devices.

Best for on-device English captioning on Raspberry Pi class hardware. Pricing: free.

Category
Open source
License
—
Stars
—
Last push
—
Pricing
free
Platforms
Linux, macOS, Windows, Android, Edge

What it is

A family of fast, accurate English-only ASR models from Useful Sensors. MIT.

Best for: On-device English captioning on Raspberry Pi class hardware.
Watch out for: English-only; 27M params for the smallest model.

Install / use

pip install useful-moonshine

Features

Speaker diarizationNo
Word-level timestampsYes
Streaming / real-timeYes
Languages supported1
HIPAA eligibleNo

Moonshine vs Whipscribe

FeatureMoonshineWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfreefree beta
Speaker diarizationNoYes
Word timestampsYesYes
StreamingYesNo
Languages199
PlatformsLinux, macOS, Windows, Android, EdgeWeb, API, MCP

Alternatives to Moonshine

OpenAI Whisper
OpenAI

The reference open-source multilingual ASR model from OpenAI.

OSS · MIT ★ 98.1k
whisper.cpp
Georgi Gerganov

C/C++ port of Whisper — runs on anything, from a Raspberry Pi to Apple Silicon.

OSS · MIT ★ 48.8k
faster-whisper
SYSTRAN

4× faster than reference Whisper using CTranslate2 — production sweet spot.

OSS · MIT ★ 22.3k

Whipscribe is a managed faster-whisper + whisperX service. If you want transcripts without running infrastructure, paste a URL or drop a file in the form below — you'll have a transcript in seconds.