Collection

code

stt-web

Transcribes speech to text live in the browser, in English and French.

model

kyutai/stt-1b-en_fr, by Kyutai

Q4_0 quantization for WebGPU by Idle Intelligence.

CC-BY-4.0

code

llm-web

Runs a tool-calling language model entirely in the browser, no server required.

code

tts-web

Converts text to speech in the browser with two lightweight voice models, multilingual Pocket TTS in review.

model

KittenML/kitten-tts-nano-0.8, by KittenML

Safetensors conversion for candle inference by Idle Intelligence.

Apache-2.0

model

kyutai/pocket-tts-without-voice-cloning, by Kyutai

Q8_0 GGUF quantization for the browser by Idle Intelligence.

CC-BY-4.0

model

kyutai/pocket-tts-without-voice-cloning, by Kyutai

Channel-wise INT8 quantization by Idle Intelligence.

CC-BY-4.0

code

sts-web

A full-duplex speech-to-speech assistant running entirely client-side, still early and rough.

model

nvidia/personaplex-7b-v1, by NVIDIA

Pruned, QLoRA-recovered, Q4_K quantization for WebGPU by Idle Intelligence.

NVIDIA Open Model License

model

nvidia/personaplex-7b-v1, by NVIDIA

Q4_K quantization for WebGPU by Idle Intelligence.

NVIDIA Open Model License

code

mimi-rs

A Rust implementation of an audio codec that tokenizes and reconstructs speech.

code

vad-rs

Detects the start and stop of speech in an audio stream using a small neural model.

model

snakers4/silero-vad, by Silero Team

Safetensors conversion for candle inference by Idle Intelligence.

MIT

code

t0-web

A from-scratch port of a probabilistic time-series forecasting transformer to the browser.

model

theforecastingcompany/t0-alpha, by The Forecasting Company

Q4_0 quantization for WebGPU by Idle Intelligence.

Apache-2.0

model

theforecastingcompany/t0-alpha, by The Forecasting Company

Q8_0 quantization for WebGPU by Idle Intelligence.

Apache-2.0

model

theforecastingcompany/t0-beta, by The Forecasting Company

Q4_0 quantization for WebGPU by Idle Intelligence.

Apache-2.0

model

theforecastingcompany/t0-beta, by The Forecasting Company

Q8_0 quantization for WebGPU by Idle Intelligence.

Apache-2.0

code

llm-life

Uses a small language model's logits as the update rule for Conway's Game of Life.

model

Qwen/Qwen2.5-0.5B-Instruct, by Qwen

LoRA adapters trained by Idle Intelligence.

Apache-2.0

model

stencil-life

Trained from scratch by Idle Intelligence.

MIT

code

hive-ml-classifier

A small BERT-mini classifier that routes chat messages into intent categories.

model

inference-at-home

Trained by Idle Intelligence.

code

ridgeline

A 3D globe visualizer that renders planetary terrain as stacked ridgeline plots.

dataset

ridgeline-terrain

Built by Idle Intelligence from public-domain government elevation data.

CC0-1.0

code

weather-web

A weather estimate for any point on Earth from the nearest METAR-reporting stations.

dataset

metar-stations

Built by Idle Intelligence from the Iowa Environmental Mesonet ASOS/AWOS network.

CC0-1.0

code

sensors-web

A page that probes which device sensors a mobile browser exposes without a permission prompt.

code

nordcoop-bench

A reproducible benchmark comparing local language models against hosted references on constrained hardware.