heatdrop.ai

This Codex Skill turns Chinese articles into hand-drawn, slightly absurd 16:9 illustrations where a deadpan black blob does the conceptual heavy lifting.

Curated prompts and API patterns for OpenAI's GPT-Image-2, organized by real use case rather than vibe or aesthetic.

Voicebox bundles seven TTS engines, Whisper dictation, and MCP agent hooks into a single Tauri app — all offline.

A crowdsourced library that reverse-engineers GPT-Image2 examples into structured, reusable prompt templates for automation workflows.

A research family of ASR and TTS models built on the bet that voice should be processed as long-form narrative, not chopped into seconds-long shards.

A curated, multilingual prompt library for OpenAI's GPT Image 2, with preview images and Raycast snippet support.

MisoTTS brings Sesame-style conversational speech synthesis to local hardware, with a Llama backbone and a stubbornly English-only vocabulary.

OmniVoice Studio runs voice cloning, dubbing, and dictation locally on macOS, Windows, and Linux — no API keys, no cloud, no subscription.

A TypeScript skillset that turns a single photo into meshes, gaussian splats, and sound effects by orchestrating multiple generative models through Claude.

Outpainting is the appetizer; the main course is automated 2D game asset generation with seam-aware tooling that exports engine-ready packs.

A Gradio-based web UI that crams every community trick for image generation into one browser tab.

React prototype that wires multiple image-to-3D APIs into a single presentation-ready studio.

VoxCPM2 generates speech directly from text using continuous diffusion, no discrete audio tokens required.

Pixelle-Video wires LLMs, image/video generators, TTS engines, and ffmpeg into a single Streamlit app that spits out short-form videos from a topic string.

A solo-built TypeScript studio that turns Chinese web novels into AI-generated storyboards, characters, and voiced video.

A 1.7B-parameter speech model that streams its first audio packet after a single character and takes voice design instructions in plain English—or Chinese, or nine other languages.

Deep-Live-Cam swaps faces in real time using a single source image and your laptop camera.

A TypeScript stack that automates scriptwriting, storyboarding, and video synthesis for the short-drama gold rush.

A visual programming interface for image, video, 3D, and audio generation that treats model pipelines as composable graphs.

A research framework that uses a multimodal LLM to plan video edits semantically, then hands off to a diffusion transformer to actually draw the frames.