#jqsp

Seedance 2.5 looks the best, but 10 seconds costs about $1, so a two-minute video easily runs over $14. To save money we switched to H3 on jqsp, and the same explainer with a host costs under $0.50.

Intermediate tutorial: Give your AI agent the ai-host-video Skill and connect it to the video platform jqsp.com. Set up the host, background extras and voice once. After that, each video only needs the video type, the target audience and the website URL. Your AI agent reads the site as the Skill describes, writes the copy and a three-shot script, checks every storyboard frame, renders, then adds B-roll and bilingual voiceover. In our test, a two-minute bilingual video cost about 169 credits, or about $0.42. Includes 4 copy-paste prompts.

Use when the user gives a URL, product page or tutorial page to promote and wants an explainer or promo video with a host on camera. The agent reads the page, writes copy and a three-shot script, builds a lip-synced host and silent background extras on jqsp.com, checks each storyboard grid panel by panel, adds B-roll, captions and a QR code, then makes a second-language dub with local F5-TTS. Every paid step is quoted first, no numbers are invented, and no one else's likeness is used. Use case: In one line: give your AI agent a URL, and it makes an explainer video with a host, background extras and a bilingual voiceover.

Entry point and router for every public jqsp.com API — read this file first for short dramas, medium-length videos, single videos, talking-head videos, image generation, storyboard sheets and voice-over / text-to-speech. Uses the Drama Agent API (https://jqsp.com/api/v1/drama/**) to take a short drama from source text to finished episode; single videos go through the jqsp-video skill, talking-head videos through the jqsp-talking-head skill, images / Nano Banana / storyboard sheets through the images sub-skill, speech synthesis through the tts sub-skill, and balance, model prices and model availability through GET /api/v1/catalog and /api/v1/model-status. At the start of a session, offer the human a set of entry buttons (new drama, continue a project, add a character / scene / prop, shot-by-shot production, export, make a medium video, make a single video, generate images, voice-over, etc.); a click goes straight into that flow. Recommend that the human writes the script on the website (step 1); with several projects, ask which one to work on (step 2 — never pick yourself); then check whether the project already has a script / storyboard (step 0): projects already in production take "continue with new chapters", projects without a script or without any broken-down chapter take "build from scratch". Along the way, GET .../status's next.tool tells you which sub-skill to read (script / characters / scenes-props / voices / storyboard); medium videos (project mode = quick15) go straight to the quick sub-skill. Use for any request like "make me a short drama", "continue this project", "where is this drama stuck", "render chapter N", "make a 15-second video", "generate an image", "make a 9-panel storyboard sheet", "turn this text into speech", "check my balance / model prices / which models work". Use case: Let your AI agent make short dramas and mid-length videos, plus images, voice-overs and single clips. It quotes the credit cost and waits for your confirmation before every spend.