The official collection of ONNX voice models for the Piper offline TTS engine, covering many languages at several size and quality levels.
hexgrad/Kokoro-82M
Indexed from Hugging FaceLinked to its home on Hugging Face. FrontierOS indexes it; nothing is hosted or mirrored here.ModelText to speech82M paramsEst. Single-board computerEstimated minimum compute for inference: Raspberry Pi 5 class CPU. Not a benchmark.Apache 2.0
About
An 82M-parameter text-to-speech model built on StyleTTS 2 components, shipped with a set of preset voices across several languages.
Why it matters for physical AI
It gives robots and device hosts natural-sounding speech on CPU-class hardware under a permissive license.
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 hexgrad/Kokoro-82MUses the Hugging Face CLI (pip install -U huggingface_hub). This downloads the whole repo; add --include "<pattern>" to fetch only the files you need.
Which offline voices should Gotchi Local ship next?
Today Gotchi Local can download Whisper.cpp for transcription and a Piper voice for speech, both from Hugging Face, as offline fallbacks for when it is not using the FrontierOS backend.
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.
More text to speech
Browse allA 100M-parameter CPU-oriented TTS model from Kyutai with voice cloning from a reference clip and support for English plus five other European languages, designed to run faster than real time using two CPU cores.
A conversational speech model that produces Mimi audio codes from text and prior dialogue audio, so its prosody follows the flow of the conversation.