동영상·이미지·음성 스킬

Record website interactions with Playwright to create demo clips, app walkthroughs, and footage for Remotion videos. The guidance covers screen dimensions, action timing, visible click effects, and converting recorded WebM files to MP4.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Recording app walkthroughs
• Demonstrating form submission and login
• Preparing browser footage for Remotion

Generate narration, dialogue, sound effects, and music with ElevenLabs APIs for videos, podcasts, and games. The skill covers voice settings, pronunciation, pauses, voice cloning, and using measured audio lengths to synchronize scenes in Remotion, a video creation framework.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating narration for videos or podcasts
• Generating sound effects from written descriptions
• Composing instrumental background music

Download videos, audio, and subtitles from YouTube and other supported sites using yt-dlp. Choose resolution and output filenames, extract MP3 audio, or inspect titles, durations, and other video details without downloading the media.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Saving videos at a chosen resolution
• Extracting MP3 audio from a video URL
• Downloading subtitles without the video

Generate sound effects and ambient audio from written descriptions using ElevenLabs. Create cinematic impacts, app notification sounds, or background textures, with controls for duration, seamless looping, and how closely the sound follows the description.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create impact sounds for videos
• Generate looping rain or forest ambience
• Make notification sounds for apps

Transcribe audio and video with ElevenLabs Scribe v2 in over 90 languages. Identify different speakers and capture word timings for meeting records, interviews, and subtitle preparation, with live transcription also covered.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Transcribing meeting recordings with speaker labels
• Preparing timed text for video subtitles
• Transcribing interviews with specialized terms

Generate HeyGen videos from text prompts or specify avatars, voices, scripts, and scenes for controlled production. This deprecated skill covers explainers and presentations; its replacement skills separate prompt-based generation from detailed avatar video creation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Generating explainer videos from text prompts
• Creating avatar presentations with an exact script
• Specifying avatars and backgrounds for each scene

Build Remotion videos using the toolkit’s shared backgrounds, comparison layouts, presenter overlays, and custom scene transitions. Apply its 30fps timing conventions and rendering practices to assemble scenes and coordinate them with voiceover.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Add glitch or light-leak scene transitions
• Show two videos side by side
• Overlay a presenter or corner logo

Edit local video files with ffmpeg, a command-line media tool. Trim and join clips, resize for social platforms, adjust playback speed, extract or replace audio, add image overlays, and export compressed or converted files.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Trimming and joining video clips
• Resizing videos for social platforms
• Extracting or replacing audio

Generate multilingual narration from scripts in OpenMontage using Azure AI Speech. Choose a voice, adjust speaking rate, pitch, and supported delivery styles, then save individual narration segments as MP3 or WAV files.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating narration for explainer videos
• Generating voiceovers in multiple languages
• Adjusting narration speed and delivery style

Create explainer, demo, or marketing videos from a written idea using HeyGen's Video Agent. It handles scripts, avatars, visuals, voiceover, pacing, and captions, then provides a download URL when generation finishes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create a product demo from a written description
• Turn an explanatory topic into a video
• Draft a marketing video

Create short video clips from text or still images with LTX-2.3 22B. Generate supporting footage, animated backgrounds, or moving portraits while specifying camera motion, lighting, dimensions, and duration, with clips around five seconds by default.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Generate supporting footage for narrated videos
• Add subtle motion to slide backgrounds
• Animate still portraits

Translate and dub existing videos with HeyGen to create versions in multiple languages. Preserve the speaker’s voice characteristics, match lip movements to translated speech, or choose audio-only translation without adjusting the video’s lip movements.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create multilingual versions of a product demo
• Dub videos with matching lip movements
• Translate audio without changing lip movements

Turn text into standalone speech audio with HeyGen's Starfish model for narration, voiceovers, or podcasts. Choose voices by language or gender, adjust speed and pitch, and add pauses when the selected voice supports them.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Generate narration from a script
• Create speech audio for podcasts
• Find voices by language or gender

Inspect video content locally by extracting frames with ffmpeg and transcribing speech with Whisper. The skill produces timestamped image paths, transcript segments, and video details in JSON, giving an agent material for visual review without requiring API keys.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing scenes and speech in a local video
• Transcribing video audio without API keys
• Extracting frames at scene changes or regular intervals

Create 3D objects from text or images, choose catalog assets for repeated scenery, and inspect the results in Blender. The workflow checks geometry, materials, scale, and ground contact while recording asset sources and generation costs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create a unique 3D object from a text description
• Reconstruct a 3D object from a concept image
• Populate scenery with catalog vegetation and rocks

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

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

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

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

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

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

Create and edit bitmap images, such as photos, illustrations, product mockups, and game assets. Use reference images for visual variations, replace backgrounds, remove objects, or make transparent cutouts while preserving specified parts of an existing image.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create photos or illustrations for a website
• Replace a product photo background or remove unwanted objects
• Make transparent cutouts

Create a Dubai weather card from a supplied temperature and unit. The skill writes an SVG, a scalable image format, and a Markdown summary to designated files, preserving the provided temperature exactly.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Turning a Dubai temperature reading into a weather card
• Saving a temperature summary in Markdown
• Updating weather image and summary files in a workflow

Add a ten-second HyperFrames scene featuring a single feature card orbiting a sphere made of dots. Customize the title, description, accent color, and orbit angle while retaining the supplied camera movement and animation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Introducing a product feature with a moving card
• Adding a ten-second scene to a HyperFrames video
• Matching a feature card's text and color to a project