Moonshine
STT.ai does not run this model. This page is reference information about it.
Transcribe with the models we do run →
7.8%
WER
1
Languages
80.0x
Speed
MIT
License
About Moonshine
Moonshine is an extremely compact speech-to-text model designed for resource-constrained environments. At only 61M parameters, it runs efficiently on edge devices like Raspberry Pi while maintaining reasonable English transcription accuracy.
Languages Supported by Moonshine
Model Info
- ProviderUseful Sensors
- Architecture-
- LicenseMIT
- UpdatedMar 2026
Frequently Asked Questions
Moonshine is a speech-to-text model by Useful Sensors. STT.ai does not currently run Moonshine — this page is reference information about the model. For transcription on STT.ai, the model picker offers the Whisper family (Turbo, Large V3, Medium, Small).
On standard benchmarks, Moonshine achieves around 7.8% Word Error Rate. Real-world accuracy depends on audio quality, accent, and language; for noisy or accented recordings, expect a few percentage points higher WER.
Moonshine is not available on STT.ai. Its own licence terms govern running it yourself. STT.ai's free tier covers the Whisper models we do run — 600 minutes to start, then a monthly free top-up.
Moonshine is released under MIT, a permissive open-source license. You can self-host Moonshine on your own hardware or use our hosted version — both are commercially usable.
Moonshine supports 1 languages. Auto-detection picks the right language for most audio; you can also specify it manually for a small accuracy lift.
Moonshine processes audio at about 80.0x real-time on our GPUs. A 1-hour audio file finishes in under 1 minutes; longer files queue and notify by email when done.
Moonshine has 61M parameters. Larger models tend to be more accurate but slower; STT.ai hosts Moonshine on GPU so the parameter count doesn't affect your client-side performance.
Moonshine accepts every format STT.ai supports — MP3, WAV, M4A, FLAC, OGG, MP4, MKV, MOV, WebM, AVI, and others. Output as TXT, SRT, VTT, DOCX, JSON, or PDF.
Yes. Speaker diarization runs alongside Moonshine for every transcription — each speaker is labeled and you can rename them in the editor afterwards.
Yes. Moonshine runs in our managed environment — audio is processed and deleted by default and never used for training without explicit opt-in. Pro plans add client-side encryption for transcripts at rest.
Use the compare-stt tool to run Moonshine against any other supported model on the same audio — you'll see WER, segment count, speaker labels, and confidence scores side-by-side. The Moonshine vs Whisper Large V3 comparison is the most commonly run.
Yes. Specify "moonshine" as the model parameter on the /v1/transcribe endpoint. Python and Node.js SDKs include Moonshine examples. Free API tier includes 100 minutes/month.
Yes. Because Moonshine is MIT-licensed, you can self-host it. STT.ai's open-source page lists the project repo and weights. Most production teams use our hosted version to skip GPU procurement, model swaps, and ops.