동영상·이미지·음성 스킬

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Separate audio parts for a remix
• Prepare a karaoke backing track
• Isolate parts for sampling

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Set up a connection before using music skills
• Check a missing or unhealthy cogmusic connection
• Replace an expired or revoked access token

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Retrieving metadata and an audio URL by production ID
• Checking whether stem separation has finished
• Checking MIDI extraction or mastering status

List saved tracks in a connected Cognitum Music account, newest first, with titles, durations, IDs, processing status, and audio links. Find tracks by part of their title and obtain the IDs needed for subsequent music tasks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing saved tracks
• Finding a track by part of its title
• Checking stem, MIDI, and mastering status

Extract MIDI or a score from an already generated music production using pitch tracking. The skill checks that MIDI is available and directs users to the dashboard for downloading it for transcription, arranging, or music software import.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Transcribing a previously generated track
• Using extracted MIDI for arranging
• Importing generated music into a DAW

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Generating narration with a saved voice
• Transcribing recordings and creating subtitles
• Managing dubbing while preserving timing and background audio

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Turn a prepared passage into spoken audio
• Render a dialogue with different voices for each speaker
• Combine a long narrated script into one audio file

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding photos from a trip or event
• Searching for photos taken near a specific place
• Checking photo details and capture dates

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choose a voice that matches a preferred sound
• Create a new custom speaking voice
• Compare two or three existing voices

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Turning a Muse experience recording into a vertical clip
• Adding chat exchanges in sync with narration
• Showing actual pages and files alongside a creator's story

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create a podcast with several speakers
• Turn key points into an audio briefing
• Produce recurring episodes with consistent hosts

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create an animated product walkthrough
• Explain a message through moving text and graphics
• Build a portrait animation for video export

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating Mandarin narration for explainer videos
• Comparing short samples of voices and speaking speeds
• Building subtitles from character-level timestamps

Generate images, video, and music through ComfyUI in OpenMontage. Helps adapt community workflows, select the final output, identify missing models, and choose workflows suited to available GPU memory while recording settings for reproducibility.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Generating images, video, or music in OpenMontage
• Importing a community ComfyUI workflow
• Choosing workflows for limited GPU memory

Helps agents prepare image, video, speech, music, and avatar generation requests with an exact model and API host. It explains service-specific inputs, request validation, and job resumption so unavailable models are not silently replaced.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Specify an exact model and API host for media generation
• Prepare image edits with reference images and masks
• Resume a timed-out generation job without submitting it again

Routes video requests to the appropriate HyperFrames workflow based on the source material and intended result. It guides agents toward specialized steps for product promos, explainers, captions, motion graphics, music videos, and HTML-based video compositions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choose a workflow for a product launch video
• Turn an article or notes into an explainer video
• Add captions or graphic overlays to a talking-head video

Guide HyperFrames video projects from setup through layout checks, editable previews, and video output. Covers command-line workflows, environment troubleshooting, and distributed rendering on AWS Lambda, which splits video rendering work across cloud functions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Setting up a HyperFrames video project
• Checking text overflow and scene display
• Exporting a video after reviewing it in Studio

Build HyperFrames animations from small motion recipes, scene templates, and transitions. The skill guides runtime selection, including GSAP, Lottie, and Three.js, and provides an audit script to examine timing and choreography while following HyperFrames requirements for reproducible rendering.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Combine motion recipes into a scene
• Build a multi-phase brand reveal from a template
• Design transitions between scenes

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Add rain or snow overlays
• Animate leaves, feathers, and floating particles
• Create simple character walk cycles

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating background music timed to a video
• Generating a song with custom lyrics
• Checking generated audio duration and quality

Find and install reusable blocks and effects for HyperFrames, then connect them to an existing composition with timing and layer settings. The skill also guides creating, validating, and contributing new blocks or components.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Add a reusable chart block to a video
• Merge a grain overlay into an existing composition
• Adjust block timing and layer order

Produce short motion graphics for animated text, numbers, charts, logos, and social overlays. Guides asset sourcing, shot design, composition, rendering, and validation, with output as an MP4 or a transparent video overlay.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Animate headlines and short text
• Show key numbers and charts in motion
• Create a short logo reveal

Generate cinematic clips with Seedance 2.0 using camera directions, multiple shots, and synchronized speech, sound effects, and ambience. Reference images help maintain character appearance, while the skill guides prompt structure, provider selection, previews, and checks of the finished clips.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Producing trailers and teaser clips
• Generating multiple shots with a consistent character
• Creating dialogue scenes with matching mouth movements

Build editable Three.js worlds from text or structured briefs, with terrain, distinct regions, landmarks, vegetation, and camera paths. Review the environment from multiple viewpoints and refine selected areas while preserving the overall layout and reproducible settings.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build a continuous 3D landscape from a written brief
• Plan a camera fly-through across distinct regions
• Refine one area's terrain or vegetation placement