Generate images through OpenAI-compatible /v1/images/generations APIs such as gpt-image-2, custom proxy endpoints, or self-hosted image gateways. Use when the user asks to test an image-generation endpoint, adapt a script to a base URL/API key/model, generate one or many images from prompts, or package a reusable OpenAI-compatible image generation workflow.
Use when performing deep analysis of China-related equities, especially A-share, Hong Kong-listed Chinese companies, Chinese ADRs, sector comparison, investment decision comparison, valuation analysis, risk review, discovering comparable stocks, or producing beginner-friendly beautiful HTML stock dashboards and optional PDF exports.
Use when screening, discovering, ranking, or building a beautiful HTML dashboard for potential China-related stocks, including A-share, Hong Kong, and Chinese ADR candidates. Especially for requests like 潜力股筛选, 挖掘机会, 找低估成长股, 行业机会, 股票池, 下一只可能走强的票, 深度洞察候选股, or multi-factor stock selection.
Generate high-quality Telegram voice notes (bubbles) using Microsoft Edge TTS and FFmpeg. Use when asked to send audio as a voice message, or when the user requires voice-bar replies instead of audio files. Handles edge-tts generation and OGG/Opus conversion for native Telegram voice compatibility.
Smart video editor for talking-head / oral-broadcast (口播) videos. Use when user sends a video file and asks to cut, trim, edit, or clean up a talking-head video. Handles: silence removal, subtitle burn-in, loudness normalization, jump-cut assembly. Default mode: silence-only cutting (simple and reliable). Filler-word cutting available via --filler-words flag but disabled by default. Supports Chinese and English speech. NOT for VFX, color grading, or non-speech video editing.
Generate 5-view multi-angle images (front/side/back/top/45-degree) from one or many input photos using the Qwen Image multiple-angles 3D camera Gradio app (Hugging Face or ModelScope mirrors). Use when user asks to create multi-angle turnarounds, camera angle variants, or batch process 10+ images into consistent view sets and return a zip. Prefer API-based Gradio calls (no browser automation) with retries, stable filenames, and quota/queue handling.