A speech-input LLM that feeds Whisper encoder features through a learned projector into Llama 3.2 1B Instruct, so it can respond to spoken input without a separate transcription step. It replies in text, so pair it with a TTS voice.
moonshine-ai/moonshine-streaming-small
Indexed from Hugging FaceLinked to its home on Hugging Face. FrontierOS indexes it; nothing is hosted or mirrored here.ModelSpeech to text123M paramsEst. Single-board computerEstimated minimum compute for inference: Raspberry Pi 5 class CPU. Not a benchmark.MIT
About
The small size of the Moonshine Streaming family, an English-only encoder-decoder recognizer that uses a sliding-window encoder so it can transcribe live audio with low latency on edge hardware.
Why it matters for physical AI
It brings live speech-to-text to Raspberry Pi-class robots and appliances without a GPU or a cloud round-trip.
Summary written by FrontierOS in our own words. The upstream card and license govern use. Metadata checked 27 Sep 2026. Read the full card on Hugging Face
Files, weights and version history live on Hugging Face. FrontierOS indexes this repo; it does not host or mirror it.
hf download moonshine-ai/moonshine-streaming-smallUses the Hugging Face CLI (pip install -U huggingface_hub). This downloads the whole repo; add --include "<pattern>" to fetch only the files you need.
What's the lowest-latency fully local voice loop you've built?
A typical cascade is voice activity detection, a turn detector, streaming speech-to-text, a small language model and a fast text-to-speech voice.
What actually runs well on a Raspberry Pi 5?
Our compute tiers are estimates based on parameter counts. Real numbers beat estimates.
More speech to text
Browse allA faster Whisper large-v3 derivative whose decoder is cut from 32 layers to 4, giving multilingual transcription in roughly 100 languages at a small accuracy cost (it was not fine-tuned for translation).
A FastConformer encoder with a token-and-duration transducer decoder that transcribes 25 European languages with punctuation, capitalization and word-level timestamps.