Speech-to-text

Moonshine Streaming Medium requirements, license & speed

By Moonshine AI (Useful Sensors) · released 2026-01-06 · 245M parameters

Hugging Face ↗ GitHub ↗ Compare

Commercial useYes
Min memoryTargets sub-1 GB memory edge devices
Runs on CPUYes
StreamingYes

Key facts

License
mit source
Commercial use
Yes source
MIT (streaming models are MIT in all languages)
Parameters
245M source
Tiny 34M / Small 123M variants also available
Minimum memory
Targets sub-1 GB memory edge devices source
Design target, not a measured minimum
Runs on CPU
Yes source
Built for edge-class hardware
Streaming
Yes source
Voice cloning
n/a (speech-to-text)
Languages
en source
Released
2026-01-06 source
Hugging Face repo creation date (proxy for release date)
Gated on HF
No

Measured speed & memory

Benchmark pending. We haven't measured Moonshine Streaming Medium yet. Planned targets: CPU (8 vCPU), Apple Silicon Mac, RTX-class consumer GPU and a rented cloud GPU. Get notified.

Similar STT models

Spotted an error? Report it. Every fact links to the model card or repo it came from.

New open speech models, tested. Weekly.

One email when a model ships: license, memory, and real speed on a Mac, a gaming GPU and a cloud GPU.