Wanted

80+ free AI services for chat, image, video, voice & APIs (may sometimes include access to lead gen ai models for free)

List of all local & free open-source voice-clone TTS models and music generation models.

The most advanced frontend drag & drop page builder. Create high-end, pixel perfect websites at record speeds. Any theme, any page, any design.

talkie is a vintage language model from 1930

Contribute to VikingOwl91/polyscribe development by creating an account on GitHub.

Arabic speech recognition, classification and text-to-speech.

Official code, models, and data for Vista4D: Video Reshooting with 4D Point Clouds (CVPR 2026 Highlight)

ProdIA-MAX is an advanced fork of fspecii/ace-step-ui paired with ACE-Step v1.5. Adds AI Music Chat Assistant, visual Chord Progression Editor, floating LoRA Manager, Demucs vocal separation, automatic ID3 tagging, full i18n support (EN/ES/ZH/JA/KO), extended presets, section-by-section generation, and multiple backend reliability fixes.

Source code for free AI video upscaler tool

I have made a simple YouTube view bot using Python. Not every view counts because of how YouTube works. I ran it for a few minutes and got over 50 views.

GUI-focused roop

🎨ComfyUI standalone pack for Intel GPUs. | 英特尔显卡 ComfyUI 整合包

Agent Skills

LLM驱动的 A/H/美股智能分析器：多数据源行情 + 实时新闻 + LLM决策仪表盘 + 多渠道推送，零成本定时运行，纯白嫖. LLM-powered stock analysis system for A/H/US markets.

A new one shot head swapping approach

OpenAI Privacy Filter

KnowFlowRAG

Text-to-music generation with MusicGen on Apple Silicon (MLX)

🎬 ScreenToGif allows you to record a selected area of your screen, edit and save it as a gif or video.

Vue数据可视化组件库（类似阿里DataV，大屏数据展示），提供SVG的边框及装饰、图表、水位图、飞线图等组件，简单易用，长期更新(React版已发布)