marswave.ai publishes skills that let an AI agent work with audio and video, covering text-to-speech narration, voice cloning from reference audio, end-to-end audio generation from text or images, AI music generation and editing, and podcast, explainer video and slide deck creation. The author's popular skills also connect agents to Google Calendar for reading and managing events and agendas, and the skills are largely triggered by both Chinese and English phrasing.
Skills
19 skills · 82 stars · MIT
Asr Transcribe audio files to text using local speech recognition.
Cola Avatar Pack Generate pixel-art self-portrait, profile card (自画像卡), emoji GIFs, and meme stickers.
Content Parser Extract and parse content from URLs.
Creator Creator workflow — generate platform-ready content packages.
Explainer Create explainer videos with narration and AI-generated visuals.
Google Calendar Use the bundled Google Workspace CLI (gws) to read, create, update, and delete Google Calendar ev…
Icloud Calendar List iCloud calendars and read, create, update, or delete iCloud Calendar events with the icloud-…
Image Gen Generate AI images from text prompts.
Listenhub ListenHub CLI skills router.
Listenhub Cli ListenHub CLI skills router.
Listenhub Voice End-to-end audio generation with ListenHub-Voice-1.0 (text / image → audio).
Music Generate, remix, extend, edit, and analyze AI music (Mureka).
Outlook Calendar View, create, update, and delete Outlook or Microsoft 365 calendar events with the cola-outlook-c…
Podcast Create podcasts from topics, URLs, or text.
Slides Create slide decks from topics, URLs, or text.
Tts Text-to-speech and voice narration.
Universal Email Use the bundled Himalaya 2 CLI to connect IMAP/SMTP or Microsoft Graph mailboxes and list, search…
Video Gen Generate AI videos from text prompts or reference materials.
Voice Clone Clone a voice from reference audio into a reusable private ListenHub speaker,
then use it for nar…