A comprehensive speech processing toolset for Node.js that provides offline and cloud-based text-to-speech, speech-to-text, and audio alignment tools without requiring Python or Docker.

FableCodex is a Codex plugin that enforces an evidence‑based, multi‑step workflow (goal ledgers, findings gates, verification) for code‑generation tasks, helping users avoid missed steps in larger or safety‑critical changes without altering the underlying model.

A macOS CLI tool for on-device speech transcription of files, live system audio, and microphone input using Apple's Speech.framework.

itr‑wala is an open‑source CLI that prepares Indian individual tax returns locally. It uses an LLM only to read PDFs, while a thoroughly tested Python engine does all the statutory calculations. The tool validates inputs, compares old vs. new regimes, and outputs a ready‑to‑type filing pack; you still manually submit and pay on the government portal.

A toolset consisting of a CLI and an in-game addon that uses ElevenLabs TTS to generate and play AI voiceovers for World of Warcraft NPC dialogue.

sosumi.ai is a Node‑based service that converts Apple Developer documentation (including Swift docs, HIG, and WWDC transcripts) into clean Markdown, making the content easy for AI models and automation tools to consume. It offers a simple URL rewrite, an HTTP/MCP API, a CLI, a Chrome extension, and can be self‑hosted on Cloudflare Workers or any Hono‑compatible runtime.

A self-hosted AI transcription tool that generates subtitles for personal media libraries, integrating with Bazarr, Plex, Jellyfin, and Emby.

Conversation Stenography is an open‑source Go CLI that encrypts a secret message with AES‑SIV, encodes the ciphertext into token choices of a locally‑run LLM (e.g., Llama 3.2 or GPT‑2), and outputs natural‑looking cover text. Users copy that text into any chat app; the recipient runs the same tool to decode and decrypt the hidden message. The system is fully offline, uses a shared secret phrase (PBKDF2‑derived key), and chains messages for integrity. It includes a setup wizard, simulation mode, and several CLI commands, but is a proof‑of‑concept and vulnerable to existing steganography detection methods.

An LV2 plugin for playing back neural network machine learning amplifier models using the NeuralAudio engine.

A comprehensive audio and video processing toolkit that extends OpenAI's Whisper for transcription, speaker diarization, summarization, and RAG-based video chatting.

A Vercel‑hosted template that lets authenticated users create AI‑driven coding tasks (Claude, Codex, Copilot, Cursor, Gemini, opencode). It spins up a Vercel Sandbox, runs the chosen agent, commits changes to an AI‑generated branch, and shows live logs. Built with Next.js 15, Tailwind, Neon Postgres, and Vercel AI Gateway; supports multi‑user OAuth, per‑user API keys, and optional sandbox keep‑alive for iterative work.

uni‑api is a config‑only server that presents a single OpenAI‑compatible API while routing calls to many LLM providers (OpenAI, Anthropic, Gemini, Vertex, Azure, AWS, etc.). It supports weighted and round‑robin load balancing, automatic retries, per‑model timeouts, rate limits, tool‑call passthrough, content moderation, and fine‑grained request overrides—all defined in an `api.yaml` file or via a `CONFIG_URL`. Deployable as a Docker container (one‑click Fugue button provided).

A privacy-first AI notepad that records, transcribes, and summarizes confidential meetings locally on-device to ensure data never leaves the premises.

Braindecode is a Python toolbox that brings deep‑learning models to raw brain‑signal data (EEG/ECoG/MEG). It provides dataset loaders, preprocessing, several ready‑made neural‑network architectures, and visualisation utilities, all built on top of PyTorch and MNE‑Python. Installable via `pip install braindecode`, it targets neuroscientists and ML researchers working with neurophysiological data.

NeuralPDE.jl is a Julia library that solves ODEs, SDEs, RODEs, and PDEs with physics‑informed neural networks. It auto‑generates loss functions from symbolic equations, works with Flux/Lux for GPU training, and integrates with NeuralOperators for advanced neural operator models.

A real-time transcription service that enables streaming speech-to-text using OpenAI Whisper, providing low-latency results instead of batch processing.

A speaker diarization toolkit that uses self-supervised learning and structured pruning to accurately identify who spoke when in audio recordings.

A voice-driven AI interface that allows users to interact with diverse AI characters using a variety of LLM and TTS providers, supporting real-time conversations and local voice cloning.

A Node.js library that provides plug‑in “skills” for AI coding assistants (Claude Code, Copilot, etc.) to generate Selenium, Playwright, Cypress, and other test‑automation code and run it on the TestMu AI cloud platform.

Qwen3‑ASR is a self‑hosted speech‑to‑text server that wraps Qwen3‑ASR models (0.6 B & 1.7 B). It auto‑selects a GPU‑vLLM backend or a CPU‑Rust backend, offers OpenAI‑ and Alibaba‑compatible HTTP/WebSocket APIs, supports speaker diarization, VAD‑based segmentation, batch inference, and can be deployed via Docker, custom GPU images, or offline tarballs. MIT‑licensed.

LNN is a Python library for neuro‑symbolic AI that represents logical formulas as weighted neural networks, enabling interpretable, differentiable reasoning and learning even with inconsistent or incomplete knowledge.

SDD‑RIPER Light is a lightweight, repo‑native framework that adds a control plane around LLM‑based coding agents. It defines a clear loop—restating goals, creating a minimal spec, awaiting human approval, executing, validating with evidence, and syncing results back—so agents can modify code safely, auditable and recoverable. Four modular “skills” (light, strict, codemap, new‑chat‑ready) cover daily work, high‑risk tasks, unfamiliar codebases, and hand‑offs.

DailyBrief is a self‑hosted Node/TypeScript app that aggregates 26 free news feeds, market data for 21 tickers and AI‑generated summaries into a bilingual (Chinese/English) single‑page HTML report. It supports six interchangeable LLM back‑ends, offers three deployment options (GitHub Actions + Pages, local one‑click install, or AI‑agent install), and costs only the LLM API calls (≈ $1 / month with DeepSeek).

A local AI music generation studio that creates full songs with vocals, lyrics, and music videos using the ACE-Step 1.5 XL model.

SoloDawn is an open‑source web app that automates full‑stack software development. It orchestrates multiple AI command‑line tools (Claude Code, Codex, etc.) via a primary LLM‑driven agent that spawns child agents on demand. Tasks are executed in parallel Git branches, each passing three layers of quality checks. When the generated code meets a 90‑point rubric, it is auto‑merged, delivering a production‑ready product from a simple natural‑language description.

Strands AI Functions is a Python library that turns ordinary‑looking functions into LLM‑backed agents. Using the `@ai_function` decorator you write a normal function with a docstring prompt; the library builds the prompt, calls a model (Bedrock, OpenAI, Claude, etc.), parses the typed result, and can automatically re‑prompt until user‑defined post‑conditions pass. Functions can return real Python objects (e.g., pandas DataFrames), run asynchronously, keep state in *AI Threads*, and be orchestrated as a team of threads via a coordinator that works locally or over WebSockets. Features include self‑correcting loops, economics‑aware model selection, memory‑backed optimisation, and a CLI/TUI for managing distributed agents. Install with `pip install strands-ai-functions` (optional extras for Claude, Kiro, Codex).

A lightweight, on-device voice dictation tool for macOS that uses Apple's native speech APIs to paste transcribed text into any active application privately.

Vui is an open‑source, real‑time voice‑assistant stack that stitches together speech‑to‑text, a local LLM, and a streaming TTS model (Vui Nano, 300 M parameters). It offers a WebRTC/WebSocket pipeline with turn‑taking, barge‑in, OpenAI Realtime‑API compatibility, a one‑shot voice‑note HTTP endpoint, pluggable ASR (faster‑whisper or Moonshine) and LLM back‑ends (Ollama, vLLM, OpenAI‑compatible), tool routing, voice cloning, and optional Claude‑style task delegation. Install via a one‑liner script or Docker‑compose; supports Linux + NVIDIA GPU, macOS + MLX, and mobile access via Cloudflare Tunnel or Tailscale.

A diffusion-based framework for high-quality singing voice synthesis and text-to-speech generation from lyrics, MIDI, and pitch data.

Bindu is an open‑source framework that turns any LLM‑based agent into a secure, identity‑verified, payment‑enabled internet service. It provides built‑in mTLS, DID signatures, OAuth2 via Hydra, USDC (x402) payment enforcement, skill advertising, push notifications, and polyglot SDKs (Python, TypeScript, Kotlin). With a single `bindufy()` call you get a JSON‑RPC endpoint, optional public tunneling, and deployment helpers, making it easy to build swarms, paid APIs, or regulated B2B agent integrations.

A Mac-native AI dictation app that provides private, offline speech-to-text conversion using on-device transcription engines.

A PyTorch implementation of diffusion-based generative models for speech enhancement and dereverberation, removing noise and reverberation from audio signals.

A singing voice conversion tool that uses diffusion models to transform input singing voices into a target timbre with basic pitch correction support.

An accessibility tool for VRChat and other environments that converts speech-to-text and text-to-speech, providing real-time translation and avatar integration.

tw‑legal‑rag is an open‑source Python CLI that connects to a hosted semantic‑search service containing 22 million+ Taiwanese judgments, statutes and administrative rulings. It lets you search with natural language, fetch exact case numbers, bundle results (including excerpts, case‑history and citation whitelists) into a JSON file, and run a deterministic citation‑check against LLM‑generated answers. The tool itself never calls an LLM and works without API keys, serving as a retrieval‑augmented generation (RAG) front‑end for legal AI applications.

A primitive parallel-formant speech synthesizer that recreates the retro sound of 1970s and 80s computer speech for the browser, Node.js, and CLI.

Gemini SRT Translator is a Python package that uses Google Gemini models to translate or transcribe subtitle files (`.srt`/`.ass`). It works via a command‑line tool (`gst`) or a Python API, can extract subtitles/audio from videos with FFmpeg, supports resume‑safe batch processing, model tuning, enterprise Vertex AI authentication, and can be installed as a skill for AI coding agents.

A collection of evaluation metrics for music and audio generative models, providing tools to calculate Fréchet Distance, KL divergence, and CLAP scores for long-form stereo audio.

git‑lrc is a Go‑based tool that installs a global Git hook to run AI‑powered code reviews on every commit. It sends the diff to a configurable LLM (Gemini by default), returns inline comments, risk scores, and a slide‑deck summary, and records the review status in the commit message. Free for up to 30 k LOC/month; paid plans start at $32 per 100 k LOC.

UnisonDB is an open‑source, log‑native real‑time database built for edge AI. It stores data in a B+‑Tree (BoltDB or LMDB) while streaming every write via a write‑ahead log that can be replicated over gRPC or object‑store (S3/MinIO). The system offers Raft‑based high‑availability writes, sub‑millisecond change notifications, and multi‑model support (KV, wide‑column, large objects), enabling thousands of edge nodes to stay in sync without separate streaming infrastructure.

An OBS plugin that provides real-time closed captioning for Twitch streams and VODs using the Google Cloud Speech Recognition API.

A large-scale, multi-lingual singing corpus with professional recordings and realistic music scores designed to improve AI singing voice synthesis and technique control.

deco Studio is an open‑source, TypeScript‑first platform that lets organizations run private AI agents. It provides a single Model Context Protocol (MCP) control plane for routing model calls, managing secure connections to internal tools, handling SSO/RBAC, audit logging and cost attribution. Agents bundle context, tools and policies; connections store encrypted credentials for services like GitHub, Slack or databases; and the model layer is interchangeable (OpenRouter, Anthropic, OpenAI, etc.). The system can be run locally, in Docker, or via Helm on Kubernetes, and includes full observability via OpenTelemetry.

Statewright is an open‑source Rust‑based framework that wraps LLM agents in deterministic state‑machines, enforcing per‑state tool policies, model routing, and approval gates to make code‑writing agents more reliable. It ships a CLI/TUI, host plugins (Claude Code, Codex, Cursor, etc.), and a self‑hostable Docker stack.

TorchLens is a Python library for capturing, visualizing, and intervening on the full computational graph of any PyTorch model (and preview support for other frameworks). It records every activation and gradient, provides rich per‑operation metadata, lets you query or filter tensors, draw PDF graphs, compute receptive/projective fields, and replay or modify the graph for “what‑if” experiments. The tool is validated on >11 600 architectures, with ~89 % algorithmically verified for faithful capture.

A web application for isolating or removing vocals, bass, and drums from songs using AI models like Spleeter and Demucs.

Notebook Intelligence (NBI) is an open‑source JupyterLab extension that adds AI chat, inline code generation, auto‑completion, and an autonomous notebook‑editing agent. It works with Copilot, OpenAI‑compatible APIs, local Ollama models, or Anthropic Claude (via Claude Code). Features include Claude‑specific tools, MCP‑based tool calls, multi‑language awareness, and live reload of AI‑edited files.

A text-to-speech system that preserves and compiles the original source code of the classic DECtalk speech synthesis engine for modern platforms.