Official documentation
Moonshine README
Moonshine AI (formerly Useful Sensors), GitHub (moonshine-ai/moonshine), n.d.
Read the originalRead on October 17, 2026
- What it is
- The README of Moonshine, a family of small on-device speech recognition models. It describes the models as optimized for live streaming and states that they are MIT licensed.
- How much weight it carries
- Official repository, so it is authoritative for the license and the streaming design. Its accuracy comparisons with Whisper are the project's own claims, so the guide does not repeat them as measured results.
Facts taken from this source
- The Moonshine speech recognition models are MIT licensed by default, in every language and at every size.
“The models are MIT by default too, in every language and at every size” (License section)
- The Moonshine project says its models are optimized for live streaming, with low latency because they do work while the user is still talking.
“Optimized for live streaming, with low latency by doing work while the user is still talking” (Project description)