Kyutai's full-duplex speech-to-speech foundation model in its male-voice variant, which models the user's and its own speech as parallel streams and reaches about 200 ms latency in practice.
davidscripka/openwakeword
Indexed from Hugging FaceLinked to its home on Hugging Face. FrontierOS indexes it; nothing is hosted or mirrored here.ModelWake wordEst. Single-board computerEstimated minimum compute for inference: Raspberry Pi 5 class CPU. Not a benchmark.CC BY-NC-SA 4.0Desk device
About
Pretrained openWakeWord models, small classifiers on top of a shared speech-embedding front end, that detect phrases such as 'hey jarvis' in a continuous audio stream.
Why it matters for physical AI
An open wake-word engine lets a device host listen hands-free without a cloud service, though the pretrained weights are non-commercial.
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 davidscripka/openwakewordUses the Hugging Face CLI (pip install -U huggingface_hub). This downloads the whole repo; add --include "<pattern>" to fetch only the files you need.
More audio
Browse allA 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.
A mixture-of-experts omni model with about 3B active parameters that takes text, image, audio, and video as input and replies in both text and streaming speech.