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.
pyannote/speaker-diarization-community-1
Indexed from Hugging FaceLinked to its home on Hugging Face. FrontierOS indexes it; nothing is hosted or mirrored here.ModelSpeaker diarizationEst. Single-board computerEstimated minimum compute for inference: Raspberry Pi 5 class CPU. Not a benchmark.CC BY 4.0GatedGated upstream: accept the owner's terms on Hugging Face to download.
About
The open speaker-diarization pipeline released with pyannote.audio 4.0, combining a segmentation model, speaker embeddings and PLDA-based clustering to label who spoke when, with better speaker counting than the 3.1 pipeline.
Why it matters for physical AI
Knowing who is speaking lets a robot in a multi-person room track and address the right person.
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.
Gated upstream. Accept the owner's terms on Hugging Face and sign in with hf auth login before downloading.
hf download pyannote/speaker-diarization-community-1Uses 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.