Create and understand media with Bailian.
media generation
Generates, edits, and understands images, video, and speech through Alibaba Cloud Bailian.
When to use it
Use it for image, video, speech, or multimodal generation and understanding requests, especially when Bailian is named or video understanding is requested.
Give it a media-generation or understanding request; it runs the matching Bailian command and returns generated media or analysis.
What you provide
This skill
DashScope temporary storage
Uploads local media files
local media files
Reads local media files
The bl CLI must be installed; the metadata requires the bl binary.
ffmpeg is needed only for concatenating clips, mixing audio, or assembling long-form video after generation.
The shared bailian-protocol skill must be read before execution; if it is missing, the agent must stop and run bl skill init.
API commands use DASHSCOPE_API_KEY, or authentication can be established with bl auth login --api-key.