Hugging Face
CSuite runs ONNX builds of open models from Hugging Face fully locally, in-process via transformers.js. Like Ollama models, they are downloaded once and run on your own hardware (no API key and no per-use fees), with smaller models that work well even on modest machines. It powers Supertonic TTS for offline speech and Whisper Base, Small and Large V3 Turbo for on-device transcription.
Text(6 models)
Alibaba's compact 4B instruction model with strong reasoning and multilingual capabilities.
Alibaba's ultra-compact 0.6B Qwen3 model — runs in-process via HuggingFace or through Ollama, with tool use.
Google's compact 1B Gemma 3 model — runs in-process via HuggingFace or through Ollama.
DeepSeek's compact 1.5B reasoning model distilled from Qwen2.5 — chain-of-thought on-device.
Meta's 1B instruction-tuned model — the smallest Llama, runnable in-process via HuggingFace or through Ollama.
Meta's compact 3B instruction-tuned model — fast on-device text generation.
Audio(4 models)
A faster, slimmed-down Whisper Large V3 that keeps most of its accuracy and returns timed segments for subtitles.
On-device English text-to-speech that runs entirely in the app, with ten preset voices and no API key.
A small on-device Whisper model that transcribes speech in the app with no API key, trading accuracy for speed.
A mid-sized on-device Whisper model that transcribes speech in the app with no API key, balancing speed and accuracy.