moonshine-streaming-medium-gguf is an open-source automatic speech recognition (ASR) model distributed in GGUF format for use with transcribe.cpp and similar tools. It enables developers to transcribe English audio to text efficiently on local devices. The model is suitable for building speech-to-text applications and supports quantized weights for performance.
In the Voice, TTS & speech space, Moonshine Streaming Medium takes a focused approach. It focuses on transcribing spoken audio into text using an open-source speech recognition model. It is built as an open-source project for developers building speech-to-text applications. Moonshine Streaming Medium is open source under the MIT license. Moonshine Streaming Medium is available on the command line, and it can be self-hosted.
Memoravox builds and maintains Moonshine Streaming Medium, and the product first shipped in 2026. Development happens publicly on GitHub with 176 stars and 458 commits in the last 90 days. PulseGate's similarity index finds few close equivalents — Moonshine Streaming Medium occupies a relatively distinct niche. Key capabilities include speech-to-text, ASR model, and quantized weights.
Latest indexed changes and source events
memoravox/moonshine-streaming-medium-gguf discovered by the PulseGate indexer
Other apps tracked under the same category.
