hyperframes-media
Asset preprocessing for HyperFrames compositions — local text-to-speech narration (Kokoro-82M, no API key), audio/video transcription (Whisper), and background removal for transparent overlays (u2net). Use when generating voiceover from text, transcribing speech for captions, removing background from video/images, choosing TTS voices or whisper models, or chaining TTS -> transcribe -> captions. Each command downloads its own model on first run.
来源信息
- 仓库
- cosmicstack-labs/mercury-agent-skills
- 最近来源活动
- 2026年5月18日 12:45
- 检测到的 SKILL.md 语言
- 英语
- 星标
- 490
- Forks
- 66
安装方式
默认使用会先检查来源的 Prompt;你也可以切换为直接命令,或下载本地副本。
检查来源文件
决定是否安装前,请先阅读 SKILL.md,以及 SkillsMP 当前展示的配套文件。
正在显示 SKILL.md
| name | hyperframes-media |
|---|---|
| description | Asset preprocessing for HyperFrames compositions — local text-to-speech narration (Kokoro-82M, no API key), audio/video transcription (Whisper), and background removal for transparent overlays (u2net). Use when generating voiceover from text, transcribing speech for captions, removing background from video/images, choosing TTS voices or whisper models, or chaining TTS -> transcribe -> captions. Each command downloads its own model on first run. |