AI Agent Skills

Pytorch实现的流式与非流式的自动语音识别框架，同时兼容在线和离线识别，目前支持Conformer、Squeezeformer、DeepSpeech2模型，支持多种数据增强方法。

Private and on-device speech recognition keyboard and service for Android.

文本转语音工具 - 默认 MiniMax TTS，支持切换 Edge TTS 和 Kokoro TTS (v1.1-zh)

Fully automated video maker using motion graphics and text-to-speech synthesis to turn newsletters into daily YouTube videos.

Use when a PERSONAL brand needs AI avatar video at scale — three tool tiers, four workflows for single avatar, translation, batch, and hybrid, reference image intake, fa…

Download YouTube videos with customizable quality and format options. Use this skill when the user asks to download, save, or grab YouTube videos. Supports various quali…

LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis

⏩ Fast-forwards long pauses between sentences — watch lectures ~1.5x faster (browser extension)

Dung khi mot CA NHAN muon len hinh bang AI thay vi tu quay — pipeline avatar AI: 3 tier cong cu, 4 workflow gom avatar don, dich da ngon ngu, san xuat hang loat va hybri…

Dung khi mot CA NHAN can AM THANH bang AI — clone giong noi, lam podcast, audiobook, voiceover cho video: 3 use case gom voiceover ngan cho TikTok va Reels, podcast 30-6…

Use when a PERSONAL brand needs AUDIO — voice cloning with ElevenLabs, Murf, or PlayHT, podcast production, audiobooks, and voiceover: short voiceover for TikTok and Ree…

Codex skill for turning classical Chinese poetry into cinematic, narrated, scroll-driven webpages · zlbigger.com

对已完成分析的视频进行导演与剪辑策划，再写带时间戳的中文解说并校验。work_dir 已包含 agent_narration_brief.md 与 vlm_analysis.json 时使用。适用于故事方向、片段选择、画面/原声/旁白分工、 解说写作与复核。输入 work_dir 中的理解索引；输出 recap_story_plan.j…

Local, OpenAI-compatible text-to-speech (TTS) API using Chatterbox, enabling users to generate voice cloned speech anywhere the OpenAI API is used (e.g. Open WebUI, Anyt…

Android Input Method Editor (IME) based on Whisper

Download videos and extract original post captions, audio transcripts, and metadata from video platform links. Use when the user provides Douyin, Bilibili, WeChat Channe…