Moonshine

by Useful Sensors

Tiny English ASR optimized for resource-constrained devices.

Looking at Moonshine? Try this first.

Drop your audio. Transcript in seconds. First transcript free, then $4 = 300 min

TL;DR

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

Category
Open source
License
NOASSERTION
Stars
★ 10.7k
Last push
2026-08-08
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

Links

GitHub repo ↗

Moonshine vs Whipscribe

FeatureMoonshineWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfree$4–$24 one-time packs (credits never expire) · $2 single unlock · 60 min free on signup
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 ★ 107.0k
whisper.cpp
Georgi Gerganov

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

OSS · MIT ★ 52.8k
faster-whisper
SYSTRAN

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

OSS · MIT ★ 24.8k

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.