视频·图像·音频技能

使用内置 image_generate.py 脚本生成图片, 准备清晰具体的 `prompt`。

中文简介正在准备中。当前显示原文说明。

视频分镜拆解技能（自包含，无需外部后端）。使用 FFmpeg 预处理视频并生成分镜数据。(1) 视频 URL 直接处理 `python scripts/process_video.py "<video_url>"`；(2) 本地文件先上传 `python scripts/video_upload.py "<file_path>"` 获取 URL 后再处理。需要本机安装 FFmpeg。

中文简介正在准备中。当前显示原文说明。

使用 video_generate.py 脚本生成视频，需要提供文件名和 prompt，可选提供首帧图片（URL或本地路径）。

中文简介正在准备中。当前显示原文说明。

根据文字描述生成视频，一个生成图片和视频的工作流技能。依赖 skills: byted-web-search, image-generate, video-generate。注意：此 workflow 没有执行脚本，只是一个描述性的文档。

中文简介正在准备中。当前显示原文说明。

视频编辑器，在需要视频后期制作、多个视频文件合成、视频添加音频轨道、合并多个音频文件、视频生成并烧录字幕场景时，使用该技能。

中文简介正在准备中。当前显示原文说明。

Inspects videos, extracts frames, and concatenates video clips stored in Volcengine TOS: read video metadata, capture single snapshots, batch-capture multiple frames by explicit timestamps or interval, concatenate multiple video clips, and save results locally or back to TOS. Use this skill when the user needs to get video duration or codec info, capture a poster image or thumbnail, extract frames at specific timestamps, sample frames at regular intervals, merge or join multiple video clips into one — even if they don't explicitly mention 'video processing' or 'frame extraction'.

中文简介正在准备中。当前显示原文说明。

Resizes, scales, and adjusts video resolution and dimensions using GPU-accelerated NVENC encoding via Volcengine LAS. Video resizing, video scaling, video upscaling, and video downscaling — change video resolution, enlarge or shrink video dimensions, and adjust video size for different platforms and screens. Video compression by reducing resolution and video transcoding and re-encoding with specific dimension constraints. Supports flexible min/max width and height ranges with aspect ratio preservation strategies (increase, decrease, or disable), including landscape to portrait conversion. Async submit-poll workflow with batch support. Use this skill when the user wants to resize or scale video resolution (upscale/downscale), change video dimensions for different platforms, compress videos by reducing resolution, transcode/re-encode videos with GPU NVENC, adjust aspect ratio including landscape-to-portrait conversion, adapt videos for mobile/web/social media, or batch process multiple videos.

中文简介正在准备中。当前显示原文说明。

Performs deep AI-powered analysis and understanding of long-form videos (up to 3 hours, 10GB) using Volcengine LAS large language models. Video analysis, video comprehension, and video summarization — generates comprehensive video summaries, video recaps, chapter breakdowns, event timelines, key moments, and structured content indexing. Supports behavior detection, action detection, video annotation, video tagging, and video content recognition. Enables intelligent video question answering — ask questions about video content and get AI answers. Handles long meeting recordings, lecture videos, webinars, surveillance and security footage, movies, tutorials, and any long video that needs detailed understanding. Async processing with submit-poll workflow. Use this skill when the user wants to analyze or understand long videos (up to 3h/10GB) with LLM-based deep comprehension, summarize video content or generate recaps, extract chapters/key moments/timelines from videos, do video Q&A (ask questions about video content), detect actions/behaviors in videos, review meeting recordings/lectures/webinars, or get structured video descriptions.

中文简介正在准备中。当前显示原文说明。

Removes unwanted visual elements from videos using AI-powered inpainting via Volcengine LAS. Video watermark removal, subtitle removal, logo removal, and text overlay removal — erases and cleans up watermarks, hardcoded subtitles, logos, text, and other fixed-region artifacts and obstructions from video footage. Video inpainting, video repair, video restoration, and video cleanup. Supports specifying exact bounding boxes for targeted removal and erasure. Handles videos up to 4 hours and 30GB. Use this skill when the user wants to remove watermarks from videos, erase hardcoded subtitles/captions, delete logo or text overlays, clean up video footage by removing unwanted objects, repair or restore videos by removing obstructions, do video inpainting on fixed regions, or remove visual artifacts from video content.

中文简介正在准备中。当前显示原文说明。

Generate videos using Seedance models. Invoke when user wants to create videos from text prompts, images, or reference materials.

中文简介正在准备中。当前显示原文说明。

将某个话题或者网页内容总结合成为播客音频（Podcast）。基于火山引擎豆包语音播客合成协议生成最终音频。

中文简介正在准备中。当前显示原文说明。

Previews and exports documents stored in Volcengine TOS: generate PDF/PNG/JPG previews, read page counts, resolve HTML preview URLs, and batch-export PDF pages as images. Use this skill when the user needs to convert or preview office documents (Word, Excel, PPT, PDF), export specific pages as images, get document page counts, or generate HTML preview links — even if they don't explicitly mention 'doc-preview' or 'document conversion'.

中文简介正在准备中。当前显示原文说明。

Converts audio objects stored in Volcengine TOS into PCM-oriented WAV output through TOS data-process async jobs. Use this skill when the user needs to convert audio to PCM or WAV, resample audio to 16k, convert to mono, change sample format, normalize audio for ASR pipelines, or prepare TOS audio files for speech recognition — even if they don't explicitly mention 'PCM' or 'audio conversion'.

中文简介正在准备中。当前显示原文说明。

Generate high-quality images from text prompts using Volcano Engine Seedream models. Supports multiple artistic styles and aspect ratios. Use this skill when users want to create images from text descriptions, generate artwork in various styles, create visual content for creative projects, or need AI-powered image generation capabilities.

中文简介正在准备中。当前显示原文说明。

企业直播 / LiveSaaS 控播 Skill。支持通过 `bytedlive` CLI 操作直播间（创建/配置/状态）、评论、系统消息、观众管控，以及 OpenAPI 兜底调用。覆盖场景包括：直播间生命周期管理、直播数据与观众画像分析、商品卡片运营（上架/讲解）、营销互动工具（卡券）与连麦协同控制、媒资库运维及账号/权益信息查询。触发词：企业直播、控播、直播间、ActivityId、评论、弹幕、禁言、拉黑、踢人、商品卡片、直播数据、观众画像、火山引擎 livesaas。

中文简介正在准备中。当前显示原文说明。

视频多模态理解：对视频生成描述/摘要/标签，并支持基于视频内容问答。当用户要理解视频内容、生成描述或对视频提问时触发。

中文简介正在准备中。当前显示原文说明。

火山引擎市场洞察助手。帮助用户获取品牌在各大社交平台和媒体渠道上的公开内容数据，通过 AI 筛选出真正值得关注的信息，并发现潜在商机线索。当用户提到以下任何场景时使用此技能：想知道最近网上有没有人在讨论自己的品牌或产品、想看看竞品最近在社交媒体上有什么动态、想了解某个话题或事件在网上的讨论热度和趋势、想定期获取和自己业务相关的行业资讯和热点内容、想把筛选后的内容数据接入自己的系统做进一步分析、想查看自己账号下有哪些监测任务或拉取某个任务的数据、想了解最新的中东局势关税贸易战AI大模型等热点话题的网络讨论、想查询商机线索信息获取 ACOR 评估竞争分析公司画像、提到火山引擎市场洞察 Volcengine Insight PullPost ListCustomSubsTask QueryClueInfo。即使用户没有直接提到"市场洞察"，只要涉及品牌声量追踪、行业动态了解、热点事件网络讨论、公开内容数据获取、商机查询与分析等需求，都应触发此技能。

中文简介正在准备中。当前显示原文说明。

智能视频剪辑：用自然语言描述要保留的片段/人物/事件，自动从长视频抽取剪辑（可用参考图做人物/物体匹配）。当用户要按描述找片段、提取高光或做智能剪辑时触发。

中文简介正在准备中。当前显示原文说明。

Transforms and inspects image objects stored in Volcengine TOS. Use this skill only when the task explicitly involves a TOS bucket/object key, TOS image processing, TOS-to-TOS save-as output, or Volcengine TOS image process syntax such as image/info, image/resize, image/format, image/watermark, image/draw, image/blindwatermark, or image/understanding. Do not use this skill for ordinary uploaded screenshots, local images, UI screenshot analysis, generic OCR, face detection, or visual question answering unless the user clearly says the image is a TOS object or asks to process/save it through TOS.

中文简介正在准备中。当前显示原文说明。

从视频提取音轨，并按时长/规则切分音频。当用户要从视频提取音频，或把长音频分段（切片/分片）时触发。

中文简介正在准备中。当前显示原文说明。

Upload video/audio media to BytePlus VOD (Video on Demand) storage, returning the Vid and playback references; supports local file upload (ApplyUploadInfo + TOS + CommitUploadInfo) and URL pull upload (UploadMediaByUrl); also submits frame extraction jobs on ingested media (StartExecution / Operation.Task.Snapshot), including specified time, fixed interval, specified frame, scene-change, sprite image, and output index modes. Trigger keywords: VOD frame extraction, frame extraction, extract frames, video snapshot, thumbnail, screenshot from video, StartExecution Snapshot.

中文简介正在准备中。当前显示原文说明。

Converts and transcodes audio file formats and encoding parameters using Volcengine LAS. Audio format conversion between wav, mp3, flac, m4a, ogg, aac and other audio formats. Adjusts sample rate (resample, downsample, upsample), bit rate (bitrate), channels (mono, stereo, channel mixing), audio compression, and audio quality settings via ffmpeg parameters. Supports TOS cloud storage paths and local file upload. Use this skill when the user wants to convert audio format (wav/mp3/flac/m4a/ogg/aac), transcode or re-encode audio files, adjust audio sample rate, bitrate, channels, compress audio files, resample or downsample audio, prepare audio for downstream tasks, or do any audio preprocessing.

中文简介正在准备中。当前显示原文说明。

AI-optimized web search, image search and content extraction via BytePlus InfoQuest API. Use this skill when you need to gather concise and up-to-date information from the web, find images, or extract clean content from specific URLs.

中文简介正在准备中。当前显示原文说明。

Guide a user conversationally through generating a new ad video from a template video and a user-provided product image. The host agent performs video understanding, detailed analysis, and rewrite planning; BytePlus Seedance is used only for final video generation with local product images as generation references.

中文简介正在准备中。当前显示原文说明。