
51 capabilities · 22 groups
每一项能力。
一个余额。
你的 agent 调用的能力,全部在这里,每一项都标明价格。没有 vendor 后台,没有订阅门槛。
直接输入是文本过滤。语义检索理解「要保持人脸一致」这类意图,把整个目录交给模型来挑。免费,不需要登录。
analyze-beats
1Analyse beat structure of an audio file. Synchronous — returns the beat list directly.
detect-shots
1Detect shot boundaries via TransNetV2. Synchronous — returns the shot list directly.
download-media
1Download social-media media (TikTok / Instagram / Twitter / Bilibili / …) and re-host on CDN.
fetch
1Fetch a URL and emit extracted text / markdown / raw body (--mode). Non-2xx → error.
generate-image
5Deprecated ambiguous image generation command. Use generate-image-prompt or generate-image-ref.
generate-image-prompt
1Generate a still image from a text prompt only; reference image inputs are rejected.
generate-image-ref
1Generate or edit a still image from required source/reference image URL(s).
generate-music
3Generate music from a required prompt; prompt is music direction unless --custom makes it lyrics.
generate-sound
1Generate a short sound effect (SFX / Foley / ambient / short loop) from a text description. ElevenLabs Sound Effects v2, duration 0.5–30s.
generate-tts
1Generate speech audio from text. `--provider` picks the backend (minimax / elevenlabs / elevenlabs-dialogue / voxcpm / seed-audio).
generate-video
20Generate a short video clip from a text prompt (optionally seeded with reference images / audio).
geocode
1Forward (address → coords) or reverse (coords → address) geocoding.
hyperframes
1lipsync
4Generate a talking-head video where a character's lips sync to a driving audio track. Submits one job (or N via --jobs-file) and returns {job_ref, status:'pending'}; the rendered video URL arrives via [async-callback].
motion-control
2Transfer motion / pose from a source video onto one or more target characters (services: dreamactor, kling3.0-motion). dreamactor supports multi-person via --image-urls; kling3.0-motion is single-person only.
places
1Search places / POIs near coordinates and fetch their photos.
remotion
1render-caption
1Burn SRT captions into a video. Synchronous — returns the captioned video URL directly.
search
1External web search via Baidu / Serper / Tavily / Brave, plus Baidu similar-image search.
static-map
1Bird's-eye view map image at coordinates with optional markers.
streetview
1Street-level imagery and coverage info via Google Maps.
transcribe
1Asynchronously transcribe audio to SRT subtitles. Returns {status:'pending', job_ref} immediately; the SRT lands via [async-callback] in a later turn.