Voice and turn-taking with decision models

Toolkit for low-latency voice avatars where Jev can serve as a gate that judges turn ends and turn taking from speech transcripts.

RAM-efficient Rust coding-agent harness, listed as using Jev decisions for memory pruning, browser navigation and voice routing.

macOS menu-bar Swift app that turns on-device transcribed speech into Jev typed decisions and macOS actions, confirming hard-to-undo steps.

Converts open Jev reproductions (Laya, Kev, NanoJev, PlayJev) to INT8 ONNX for offline CPU decisions at about 15.6 ms per question.

Cross-platform dictation app where a decision model chooses whether a personal-dictionary replacement actually fits the sentence.

One-page web app where Jev plays chess against OpenRouter LLMs, Stockfish or you, showing the moves it weighed and their probabilities.

Voice assistant daemon for Hyprland Linux desktops that acts through tool modules, with Jev gating which requests and actions proceed.

Liquid Glass voice typing for macOS 26 with an optional Jev fast path that types clean short sentences without waiting for LLM cleanup.

Local-first meeting transcription and conversation memory app whose live voice path runs its evaluations through Jev.

Chrome extension and web app that find YouTube sponsor reads with Jev from transcripts or audio and skip them.

Home Assistant conversation agent that maps Assist commands to built-in intents using a Jev fan-out of typed questions.

Japanese tool that has Jev fix VOICEVOX text-to-speech readings, word boundaries and optionally intonation via choice questions.

Floating live-call coach that transcribes locally and asks Jev after each sentence what to do next, shown with a confidence gauge.

Read-aloud English tutor: streaming ASR transcribes, then Jev judges word by word whether each word was read correctly.

Hackathon crisis agent that filters incoming calls and messages, plans with an LLM plus a solver, and uses Jev for in-call perception.

Mac voice assistant where one Jev call per utterance maps speech to app, volume, Spotify and system actions; an LLM only answers questions.

Talk to your Mac: local whisper.cpp transcribes, one Jev request picks the action and typed arguments, and code executes macOS automation.

Floating macOS bar for voice or text commands where Jev picks the next action from live accessibility controls in a loop.

Local web and voice interface for Codex and Claude sessions in tmux, where Jev interprets each request and Python performs it.

Proof of concept that uses Jev to detect Spanish profanity in word-timestamped audio and beeps it out with ffmpeg without changing duration.

macOS voice and typed computer-use app where Jev picks the next on-screen action from the Accessibility tree, with no screenshots.

Pre-alpha Rust and Tauri voice control layer for macOS that reads the accessibility tree; Jev is a fallback rather than the router.

Node app that controls Chromium by voice, asking Jev a dozen typed questions per partial transcript to act before you finish.

Electron app for controlling Windows 10/11 by Turkish or English speech, using OpenAI Realtime, Jev decisions, UI Automation and Playwright.

Voice-controlled Mac agent where Jev picks the tool and its arguments in about 300 ms, running AppleScript or driving Chrome.

Experimental voice-driven auto-advance for Slidev that asks Cloudflare's Clef-omni four typed questions when the presenter pauses.

Home Assistant conversation agent that resolves commands from one System One call with a fan-out of typed questions, asking when unsure.

Rails engine for voice and typed commands: define actions in a Ruby DSL and Jev picks the matching command or page control.

openvons (open-Jev): finite-choice decision layer for text, images and Japanese voice, with a none option and execute/confirm/reject.

Draw on a tldraw canvas by voice while pointing a webcam-tracked finger; Jev decides command, action, shape, colour, target and place.