视频·图像·音频技能

为功能验证或PR录屏添加字幕、局部放大和播放速度调整，制作带有操作说明的MP4，同时保留原始视频作为证据。

• 为PR录屏添加操作说明字幕
• 放大界面中的操作位置
• 缩短功能验证视频中的等待片段

Find GIFs on Tenor or Giphy, preview candidates in a terminal interface, and download selected results. Extract a still image at a chosen time or create a PNG grid of frames for review and sharing.

中文简介正在准备中。当前显示英语简介。

• Finding GIFs for a topic or reaction
• Previewing and downloading GIF candidates
• Extracting a still image at a chosen time

Turn audio into spectrograms, images showing frequencies over time, and panels of features such as loudness and rhythm. Combine views in a grid and choose a time segment, color palette, and output image size.

中文简介正在准备中。当前显示英语简介。

• Viewing audio frequencies over time
• Comparing loudness and rhythm in a panel grid
• Visualizing a selected audio segment

Turn text into speech with ElevenLabs using the sag command line tool. Choose a voice, adjust pronunciation and delivery, play audio locally, or save a file to send as a spoken response.

中文简介正在准备中。当前显示英语简介。

• Reading text aloud on your computer
• Saving spoken replies as audio files
• Choosing and checking a reading voice

使用whisper在本地转录音频文件，保存为文本或生成翻译字幕，无需API密钥。可选择不同大小的模型，根据任务需求平衡处理速度与准确度。

• 将录音转录为可阅读的文本
• 根据音频制作翻译字幕
• 按速度或准确度需求选择模型

Find meme templates that fit a joke or topic, then add captions to create an image draft. Save the result locally as SVG or PNG, or use Imgflip to generate a hosted image URL.

中文简介正在准备中。当前显示英语简介。

• Choose a meme format for a joke
• Search templates by name or topic
• Create a captioned SVG or PNG draft

使用sherpa-onnx语音模型，在本地将文字转换为朗读音频并保存为WAV文件。准备好运行环境和模型后，无需连接云服务即可生成语音。

• 将文字保存为WAV音频
• 不连接云服务生成语音
• 切换语音模型选择声音

将音频文件发送到OpenAI语音转写API，并将结果保存为文本或JSON。可指定模型和语言，也可为发言添加说话人标签，便于区分录音中的不同说话人。

• 将会议录音转为文字
• 区分访谈中的说话人
• 将转写结果保存为JSON

从网络摄像头或本地摄像头保存静态图片和短视频，支持画面中的运动监测、连接诊断，以及对兼容USB摄像头进行方向和变焦控制。

• 保存网络摄像头的静态图片
• 将摄像头画面录制为短视频
• 监测画面中的运动

Record web application demos with Playwright, a browser automation tool. The workflow explores the interface, rehearses each step, and produces WebM videos with visible cursor movement, subtitles, and readable pacing.

中文简介正在准备中。当前显示英语简介。

• Creating a video walkthrough of a new feature
• Recording tutorials for new users
• Adding operation videos to documentation

Turn visual preferences and local references into reusable style packs, validated settings for look and rhythm. Plan cuts for local footage, export editable timelines, and prepare image, video, or 3D asset plans without calling generation providers.

中文简介正在准备中。当前显示英语简介。

• Interview for visual direction and create a reusable style pack
• Validate style packs and audit their sources
• Plan local footage cuts using measured reference rhythm

Use the VideoDB Python SDK to search video by speech or visual content and create playable clips with timestamps. Add subtitles and audio, change aspect ratios, and configure alerts for live video or desktop sessions.

中文简介正在准备中。当前显示英语简介。

• Find spoken topics or visual scenes and create clips
• Add subtitles, background music, or dubbing
• Change video resolution and aspect ratio

Plan a consistent visual direction for music videos and short edits in angelcore, cloud-trance, and hyperpop styles. Define color, lighting, camera movement, and beat-synced cuts, then coordinate footage generation and editing through companion skills.

中文简介正在准备中。当前显示英语简介。

• Plan the visual direction of a music video
• Give AI-generated supporting footage a consistent look
• Design cuts that follow the song's beat

Edit existing footage into vlogs, tutorials, demos, or short social clips. This skill guides segment selection, cutting, overlays, audio additions, and platform-specific framing, with final pacing and polish handled in a traditional video editor.

中文简介正在准备中。当前显示英语简介。

• Turn long recordings into short highlight clips
• Build a vlog from raw camera footage
• Add text overlays and narration to product demos

Create and edit videos using a measured reference style for color and cutting rhythm. Combine generated clips, existing footage, overlays, and 3D props, then check visual measurements and deliver both a video and an editable timeline.

中文简介正在准备中。当前显示英语简介。

• Creating a video in a captured reference style
• Supplementing existing footage with generated clips
• Adding overlays and rendered 3D props

Measure the colors and shot lengths of reference videos to build a reusable style pack. Outputs include a LUT, a color conversion table, plus still frames, overlay assets, and a generation specification grounded in the measured footage.

中文简介正在准备中。当前显示英语简介。

• Extracting a color grade from reference videos
• Measuring cut timing for similar pacing
• Building separate style packs for each genre

Create videos in React with Remotion using focused implementation guidance and code examples. The skill covers animation, audio, captions, charts, 3D content, and scene transitions, along with handling media assets and timing.

中文简介正在准备中。当前显示英语简介。

• Creating animated text and scene transitions
• Adding audio and subtitles to videos
• Showing charts and 3D content in videos

Create short animated explainers with Manim for technical concepts, graphs, system diagrams, and product walkthroughs. Plan scenes, render a video, and prepare a thumbnail, with optional handoff for further editing or compositing.

中文简介正在准备中。当前显示英语简介。

• Explain a technical concept with animation
• Visualize changes in graphs or network diagrams
• Show a workflow or system architecture

Create images, videos, and audio with fal.ai through MCP, a connection to external tools. Find suitable models, estimate costs, edit source images, generate speech, and create sounds that match video content.

中文简介正在准备中。当前显示英语简介。

• Creating thumbnails or product images from text
• Changing an existing image's style
• Turning a still image into a video

Inspect Blender characters and animations using bone data, coordinates, and ground contact measurements alongside images. Helps diagnose foot sliding, orientation mismatches, and twisting, with reports that distinguish confirmed problems from likely causes and required fixes.

中文简介正在准备中。当前显示英语简介。

• Checking foot sliding and floor penetration in a walk cycle
• Comparing character facing direction with travel direction
• Inspecting poses after transferring motion between skeletons

Turn audio and video into text across 99 languages, translate speech into English, and create timestamped subtitles. The skill covers model selection, transcription settings, and batch processing for recordings such as meetings and podcasts.

中文简介正在准备中。当前显示英语简介。

• Transcribing recorded meetings
• Turning podcasts and videos into text
• Translating foreign-language recordings into English

Create Python workflows for generating images from text, restyling existing pictures, and filling selected regions. Using HuggingFace Diffusers, the skill explains composition controls, style adapters, generation settings, and ways to reduce memory use.

中文简介正在准备中。当前显示英语简介。

• Generate images from written descriptions
• Restyle an existing picture as a watercolor
• Fill a masked area of a photo

Generate complete songs locally from lyrics and tags describing mood, instruments, or genre. The skill guides setup, input formatting, memory-saving settings, and MP3 output using the open-source HeartMuLa music models.

中文简介正在准备中。当前显示英语简介。

• Turn original lyrics into a complete song
• Try different moods and instruments with tags
• Generate music locally or offline

Turn source text or a topic into educational, biographical, or tutorial comics. The skill develops panel plans, character descriptions, image prompts, and page images, with choices for art style, tone, layout, and language.

中文简介正在准备中。当前显示英语简介。

• Explain a difficult concept through a comic
• Tell a person's life story in comic form
• Illustrate a procedure as a tutorial comic