Moonshine Voice
An open-source toolkit for streaming speech-to-text, text-to-speech and voice agents that runs entirely on the device, with no account or API key.
About Moonshine Voice
Cloud speech APIs add latency, cost and privacy concerns, while many local models are not built for live streaming.
Who it’s for
- Developers building voice interfaces and agents
- Teams that need speech recognition on phones, desktops or Raspberry Pi
When to consider it
Consider Moonshine Voice when you need low-latency, private speech recognition in Python, JavaScript/WASM, iOS, Android, macOS, Linux, Windows or Raspberry Pi.
Tradeoffs & limitations
- Code and most models are MIT licensed, but the legacy non-streaming models for Arabic, Japanese, Korean, Mandarin, Spanish, Ukrainian and Vietnamese use the non-commercial Moonshine Community License, and the text-to-speech models carry their own third-party licences.
SOTA overview · Documentation-based assessment · Sources & review method
Updates
No updates shared yet.
Discussion
Newest firstAsk a question or share how you use Moonshine Voice.
Keep it helpful. Community rules
Loading discussion…
Sources & review method
Documentation-based assessment · Oct 31, 2026 · Prepared with AI assistance; not a hands-on benchmark.
Checked by SOTA · AI-assisted documentation review. Selection advice is our assessment; verify current requirements for your deployment.
Import history & original evidence
Moonshine Voice official website
An open-source toolkit for streaming speech-to-text, text-to-speech and voice agents that runs entirely on the device, with no account or API key.
Based on official pages and announcements checked on 2026-10-31. No hands-on test, performance benchmark or popularity ranking is claimed.