Video editing, thumbnails, comics, and audio (3.2K skills)
Separate an existing generated track into four stems: individual audio parts for vocals, drums, bass, and other sounds. Prepare material for remixes, karaoke, or sampling, then listen to the results through the dashboard.
Create a playable song from a brief describing genre, mood, language, tempo, and theme. The skill prepares structured lyrics and music instructions, generates the track through Cognitum Music, and returns its title, duration, and audio link.
Look up a music production by its ID to retrieve metadata and an audio URL. Check whether stem separation, which splits audio into parts, MIDI extraction, or mastering has finished using the production’s latest status.
Apply a mastering pass to an already generated track, adjusting perceived loudness and limiting audio peaks. See before-and-after loudness measurements, then access the mastered audio through the dashboard.
Connect a Cognitum Music account to Claude Code through the cogmusic MCP server, a bridge that exposes music tools. The skill guides token creation, local registration, connection checks, and replacement of expired or revoked credentials.
Connect agents and automated workflows to VoiceStudio to generate speech with saved or designed voices, transcribe recordings, create subtitles, and manage dubbing or narration. It uses the running backend and checks available models and capabilities.
Find personal photos in an uploaded library or connected device gallery using descriptions, dates, and locations. Inspect candidate photos and their capture details to identify the image relevant to a request.
Choose a speaking voice, create a custom voice, or restore the previous selection. Compare existing voices through a picker, or switch and hear one voice at a time during a live call.
Convert supplied text or dialogue scripts into audio files with chosen voices. Assign different voices to speakers, adjust speaking speed, and render long scripts with automatic splitting and joining into one audio file.
Turn a talking-head or selfie recording into a vertical video about a Muse experience. Preserve the original narration while showing synchronized chat exchanges, actual work outputs, interface elements, and message sounds to create a shareable clip.
Turn a topic into a scripted podcast, audio briefing, or narrated summary delivered as an MP3. Support one or several speakers, generate cover art, and manage recurring episodes or publication to an RSS podcast feed.
Create animated HTML pages with smooth scene transitions and playback controls. An editable timeline lets users adjust scene lengths and speeds, with fixed landscape or portrait layouts prepared for video export.
Build reusable data packages for local 2D character animation. Define separate body parts, rotation points, layer order, movement limits, and views so a shared renderer can animate each character using its own rig data.
Design reusable pose data for 2D characters, covering emotions, actions, mouth shapes, and repeated movements. Organize changes to individual body parts, pose durations, and transitions so animation sequences have clearly defined stages.
Turn a music track into a HyperFrames video with text, images, and clips timed to its rhythm and energy. Additional visual assets are optional, and the workflow includes storyboard approval, visual checks, and final MP4 rendering.
Generate 4–30 second videos with synchronized audio using ByteDance Seedance 2.5. Organize image, video, and audio references, write shot-by-shot prompts, and define continuity rules to keep characters and locations consistent across cuts.
Use p5.js or Canvas to create local animation effects around characters, including rain, snow, floating particles, walk cycles, and squash and stretch. Build motion from code for environmental effects and simple character bodies.
Create background music or songs with Google Lyria 3 by choosing a model and structuring musical instructions. The skill guides listening checks, measurement of actual duration, and preparation of a separate master for videos requiring an exact length.
Generate Mandarin and multilingual narration with Volcengine Doubao Speech 2.0. Choose a voice and speaking speed, save the audio, and retain character-level timing metadata for subtitles in an OpenMontage workflow.
Generate video clips from text descriptions or reference images through multiple API services. Compare available providers by cost and task needs, choose aspect ratios, track generation progress, and refine existing clips through conversational editing with Gemini Omni.
Generate short videos with MiniMax H3 from text, starting images, or reference media. The skill guides camera and motion prompts, first-to-last-frame animation, and route selection across hosted services and local ComfyUI workflows.
Find background music, sound effects, images, and icons from existing assets, shared caches, or HeyGen. Save selected files locally and register them in an inventory, giving the agent a usable file path.
Structure an HTML video project for HyperFrames, with explicit clip timing, tracks, reusable scene sections, and framework-controlled media playback. Provides rules for repeatable rendering and checks to identify composition problems before producing the final video.
Generate short videos with audio from prompts and reference images, then refine them through conversational edits. The skill covers targeted object, lighting, and text changes, plus timed actions, using Gemini Omni Flash through documented video tools.