A web application for collecting speech donations to create public domain datasets for training voice recognition-related tools.

VectorVein is a cross‑platform, no‑code desktop app for building AI‑driven automation workflows. It lets users visually connect LLM calls, embeddings, speech‑to‑text, and other nodes, supports any OpenAI‑compatible endpoint (OpenAI, Ollama, LM‑Studio, etc.), provides a local FastAPI REST API for programmatic execution, and ships as a single executable built with pywebview.

GPU‑Jupyter provides a Docker‑based, GPU‑enabled JupyterLab environment pre‑installed with Python, PyTorch, TensorFlow, Julia, and R. It offers versioned images, easy customization, and Docker‑Compose support, enabling reproducible deep‑learning experiments on any machine with an NVIDIA GPU.

TypeAgent is a Microsoft open‑source sample that shows how to build a single personal AI assistant using large language models, structured prompting, and a novel “Structured RAG” memory system. It includes an Electron shell, a dispatcher that routes natural‑language requests to typed agents, a memory layer that stores conversation facts as logical entities, and a cache to reduce LLM calls. The repo provides many example agents (calendar, email, browser, etc.) and an SDK for adding custom agents. It is early‑stage sample code, tested with Azure OpenAI in English, and not intended for production without further validation.

bnlearn is a Python library for learning, parameterising, and querying Bayesian networks. It supports structure discovery (various scores and search methods), CPT estimation, causal inference (do‑calculus), synthetic data generation, and visualisation, all wrapped in a simple API.

An open-source audio and video transcription tool that generates automatic drafts using AI and supports collaborative manual editing.

A native Pascal deep‑learning library (CAI Neural API) that runs modern LLMs, audio‑generation, image super‑resolution, and classic vision models on CPU (AVX) or OpenCL GPUs, compiled into a single binary without Python or CUDA.

Clouds Coder is a Python runtime that separates CLI execution from a browser‑based IDE, adds AI‑agent orchestration, and provides a LAN‑only collaborative workspace with versioned files, conflict‑resolution, and admin‑approved tool policies.

A collection of optimized Docker images for WhisperX, providing pre-bundled ASR models for fast and efficient speech-to-text transcription with word-level timestamps.

A tiny JavaScript library that enables users to control websites through voice commands using speech recognition.

A unified framework and API server providing a centralized interface for multiple TTS and ASR models, including ChatTTS, CosyVoice and Whisper.

FoleyCrafter is a video-to-audio generation framework that produces realistic, synchronized sound effects based on the visual content of a silent video.

A device-independent interface for speech synthesis that provides a unified API for accessing multiple text-to-speech engines.

CPA‑Helper is a self‑hosted web dashboard (Go backend + Vue frontend) for managing CLIProxyAPI/CPA accounts. It provides multi‑user analytics, per‑user API‑key handling, balance enforcement, model‑price catalogues, and health‑checks for Codex auth files, all stored locally in SQLite.

A Neovim plugin that embeds GitHub Copilot Chat (and other LLMs) directly inside the editor, offering chat, tool‑calling, custom prompts, and a Lua API for automation.

An AI-powered English speaking assistant based on Google Gemini that provides real-time pronunciation feedback and grammar corrections.

一个本地离线的语音识别字幕生成工具，支持音频、视频和麦克风录音转SRT字幕，基于Qwen3-ASR和Whisper模型，可纯CPU或GPU加速，内置多种特化语言模型、说话人分离和卡拉OK逐字模式，并附带命令行接口和OpenAI兼容API。

A ComfyUI extension that implements IndexTTS for high-quality voice cloning and text-to-speech, featuring multi-lingual support, emotion control, and multi-character novel parsing.

An OpenAI-compatible text-to-speech API service and Python SDK that converts text to natural speech using the openai.fm backend.

Ekho is a Chinese text-to-speech engine that converts written text into spoken audio, supporting custom voice data integration.

Swiftide is a Rust framework for building LLM applications with three core components: an agent harness for semi-autonomous agents, typed task graphs for workflow orchestration, and streaming RAG pipelines for indexing and retrieval.

Holistic Trace Analysis (HTA) is a Python library that reads PyTorch Profiler (Kineto) traces from distributed training jobs and produces data‑frames and visualisations showing where GPUs spend time—compute, communication, memory, or idle. It offers kernel‑level breakdowns, idle‑time causes, comm‑compute overlap, frequent kernel patterns, launch‑time stats, augmented memory‑bandwidth/queue‑length counters, and a trace‑comparison tool. Install via `pip install HolisticTraceAnalysis` (Linux/macOS, Python ≥ 3.10) and use the `TraceAnalysis` class in a notebook to get pandas DataFrames for each analysis. Documentation, examples, and an experimental CUPTI counter API are provided.

A deep-learning tool for extracting instrumental tracks from songs by separating vocals from the background music.

DeepProbLog is a Python library that merges ProbLog’s probabilistic logic programming with deep learning by introducing neural predicates—facts whose probabilities are output by PyTorch models. It supports exact and optional approximate inference, includes example experiments from its research papers, and can be installed via `pip install deepproblog`.

Rossoctl is an open‑source, Kubernetes‑native platform that intercepts AI agents via the RossoCortex data‑plane, enforcing identity, authorization, resilience and observability. It adds reusable services (skills, tools, memory, knowledge base, sandboxes) and admin tooling, enabling trustworthy, production‑grade agent deployments across frameworks.

NNStreamer provides GStreamer plugins that let developers embed neural‑network inference directly into media pipelines, supporting many AI frameworks and hardware accelerators across Linux, Android, Tizen, and macOS.

UPage is an open‑source, Docker‑based platform that uses large language models to turn natural‑language descriptions into fully responsive web pages. It offers a visual editor, multi‑page generation, and export of clean HTML/CSS/JS, and works with any compatible LLM API.

A Telegram bot that automatically converts audio messages to text using a worker-queue architecture and GPU-accelerated transcription.

Tequila is a Python framework for building and optimizing variational quantum algorithms. It provides abstract objects for circuits, Hamiltonians and expectation values, automatic differentiation, and seamless support for many quantum simulators (Qulacs, Qiskit, Cirq, etc.) and quantum‑chemistry packages (Psi4, PySCF, Madness). Users write high‑level code, call `tq.minimize`, and can run on simulators or real hardware.

A collection of development examples for Alibaba Cloud Bailian, enabling developers to implement speech recognition, synthesis, and real-time voice dialogue using Qwen-Audio and other models.

A Python framework for extracting acoustic and linguistic features from speech to detect speech disorders and recognize emotions.

A production-ready end-to-end toolkit for small-footprint wake-up word detection designed for low-power IoT devices.

A collection of cross-platform code samples demonstrating how to use the Microsoft Cognitive Services Speech SDK for speech recognition, synthesis, and translation.

BindsNET is a PyTorch‑based library for building and simulating spiking neural networks on CPU or GPU. It provides neuron models, biologically‑inspired learning rules (e.g., STDP), and tools to turn SNNs into ML or RL agents. Install via pip, Poetry, or Docker, and run examples ranging from MNIST unsupervised learning to Atari game playing.

Lean Copilot is a Lean 4 library that integrates large language models as proof‑automation tactics. It provides commands like `suggest_tactics`, `search_proof`, and `select_premises`, ships pre‑built BYT5 models, and lets users plug in any external model via a small HTTP API. Installation is done through the normal Lake package manager, and the library is ready for use in any Lean project.

A training and modeling framework for SpeechLM-based text-to-speech systems, supporting pre-training, SFT, and RLHF alignment across single or multi-GPU clusters.

OpenYak is an open‑source desktop GUI (Electron + React) that lets you chat with Codex or Claude Code agents while keeping all conversation history, files and project data locally (Rust + SQLite). It integrates the official runtimes via stdio, shows referenced files (Markdown, HTML, PDF, DOCX, code), and offers a shared Playwright‑driven browser where both user and agent can control the same page. Run it with Node 26, Rust 1.90, and your own Codex/Claude CLI binaries; the app is in v2 alpha and licensed Apache‑2.0.

LLM‑Subtrans is a Python‑based desktop and CLI tool that translates subtitle files (SRT/ASS/VTT) using LLM APIs (Gemini, OpenAI, Anthropic, etc.). It supports pluggable subtitle formats, optional audio transcription, project‑file resume, and many advanced CLI options. Install via pre‑built Windows/macOS packages or from source with a virtual‑env installer; run through a simple GUI or command line, providing the provider’s API key.

A local Node.js server that lets AI‑assistant clients (via MCP) run SQL queries on a personal Apple Health CSV export, using an in‑memory DuckDB database. It provides schema discovery, ad‑hoc queries, and health‑summary reports while keeping data on the user’s machine.

KISS Sorcar is an open‑source, local‑first AI‑agent framework that runs a daemon (`kiss‑web`) and provides VS Code, web/mobile, and Python interfaces for issuing natural‑language tasks. It supports any LLM you configure (OpenAI, Anthropic, Gemini, local endpoints, etc.), mixes multiple models in one workflow, and includes 43 built‑in third‑party agents for messaging, email, smart‑home, and productivity services. Custom Python “extension agents” let you define prompts, tools, budgets, and safety hooks per task. All prompts stay on your machine; the system handles git worktree isolation, voice wake‑word, scheduled automations, and tool calling, making it a privacy‑focused, extensible personal AI assistant.

DocuBrowse is an offline, AI‑enhanced document search tool. It indexes a wide range of file types, offers keyword, semantic, and hybrid search (using local Ollama embeddings), provides in‑document “Deep Links”, and can generate AI‑summaries of files with a local model. Everything runs locally, preserving privacy, and the app is packaged for Linux, Windows, and macOS.

An open-source universal voice-to-text interface that uses AI to transcribe and format speech into clean text, typing it directly into any active application.

AgentKit is an open‑source SDK that provides a catalog of 70 ready‑made “kits” (full apps, pipelines, or templates) for building, testing and deploying AI agents. Kits are defined by a simple config file, can be edited in a visual flow studio, and are shipped as Next.js apps that run server‑less. The collection covers support triage, code review, RAG chat, hiring assistants, legal/medical bots, and many other business‑focused agents, making it a turnkey platform for creating reliable, enterprise‑grade AI agents.

A lightweight Python package for Automatic Speech Recognition using ONNX models, eliminating the need for PyTorch or Transformers for fast deployment on edge and server hardware.

A self-hosted AI tool for real-time transcription and translation of live streams, microphone audio, and video files into English and other languages.

A family of Arabic-first generative speech recognition models that provide state-of-the-art transcription for dialectal Arabic and code-switched speech.

A Russian-language voice assistant that works offline by default and supports extensible plugins and LLM-powered natural language command processing.

PocketSphinx is an open‑source, offline speech‑to‑text engine (C library with Python bindings) that runs efficiently on low‑resource devices. It provides a command‑line tool and APIs for recognizing or aligning audio, outputting results as JSON.