SlideMaster

Use this when the user wants to plan a presentation. Generates slide titles and descriptions from a topic. Automatically creates a project and returns project_id — no need to call create_project separately.

Use this to create a new empty project. Returns the project_id needed for all subsequent operations.

Use this to upload an existing PPTX or PDF file. Returns a pre-signed upload URL and project_id.

Use this after the file has been uploaded to the pre-signed URL. Triggers server-side processing.

Upload a style reference image to analyze its visual style (colors, fonts, layout). Returns a style_guide object that can be passed to render_slides to apply this style to all slides. IMPORTANT: image_url must be a publicly accessible URL (e.g. hosted on Imgur, Cloudinary, or...

Use this to generate AI slide images for a project. Each slide gets a background image from the AI model. Optionally pass a style_guide (from analyze_style_image) to apply a consistent visual style. Each slide needs: title (displayed heading), description (visual scene descrip...

Use this to generate a narration script for a single slide using AI.

Use this to generate narration scripts for all slides in a project in one batch.

Use this to generate text-to-speech audio. Pass project_id for all slides or slide_id for one slide. Provider comparison: - **gemini**: Best quality for zh-TW/en/ja, natural intonation, recommended default. Voices: Zephyr, Puck, Charon, Kore, etc. - **cosyvoice**: Supports voi...

Use this as the final step to compile slides + audio into an MP4 video. Poll check_status afterward.

Use this when the user wants to see their existing projects. Returns a paginated project list.

Use this to retrieve detailed metadata and status for a specific project.

Use this to update project settings like title, description, TTS provider, voice, or language.

Use this to permanently delete a project and all its slides, audio, and video. Do not use for archiving.

Use this to list all slides in a project with their titles, scripts, and render status.

Use this to edit a slide's title or narration script text.

Use this to permanently remove a single slide from a project.

Use this to poll processing progress after triggering render, TTS, or video generation. Status values: - "processing": Slides are being rendered (poll every 5-10 seconds) - "parsed": Slides are rendered and ready. Check scripts/audio progress in the response. - "generating_vid...

Use this to get download URLs for all generated assets: slides, audio, and video files.

Export all rendered slides as a single PDF file (16:9 landscape, one slide per page). Returns { pdf_url, page_count, title, summary }. IMPORTANT: Give the user the pdf_url value — it is a signed download link that expires. Do NOT construct GCS URLs manually.

Export all rendered slides as a single PPTX (PowerPoint) file. Returns { pptx_url, page_count, title, summary }. IMPORTANT: Give the user the pptx_url value — it is a signed download link that expires.

Export project as an EverCam offline HTML5 playable package (ZIP). Requires video to be generated first. This is async — call evercam_status to poll progress.

Poll EverCam export progress. Returns status (processing/completed/failed/not_started) and download_url when completed.

Browse available TTS voices. Use this before generate_tts to help the user pick a voice. Providers: gemini (best quality, zh-TW/en/ja), cosyvoice (voice cloning, zh-TW/zh-CN), azure (40+ languages, widest coverage).

Check remaining API credits before starting expensive operations. Call this before large projects (>10 slides) to avoid mid-job failures. Quick reference: 2,000 credits ≈ 14 slides at 2K resolution (slides only, no TTS/video). Per-slide costs: 1K=42, 2K=140, 4K=250 credits. TT...

No parameter schema in public metadata yet.

View recent credit transaction history (purchases, consumption, monthly resets, refunds). Use this when the user asks about their billing history or wants to know what consumed their credits.

Estimate credit cost BEFORE running expensive operations. Returns per-operation breakdown, total, current balance, and whether you have enough. Always call this before render_slides or topic_to_video on large projects. YouTube cost is dynamic: min 30 credits, actual = max(30,...

Get a complete snapshot of a project in one call: metadata, all slides with script/audio status, progress summary, and what to do next. Call this after any long-running operation to orient yourself before deciding the next action.

Use this for one-click presentation creation from a topic. Default: slides only. Set include_scripts=true for narration, include_video=true for full MP4. Poll check_status afterward.

Get saved user preferences (style, voice, language, etc). Call this at the START of every conversation to auto-apply the user's past choices. Returns null fields if no preferences saved yet.

No parameter schema in public metadata yet.

Save user preferences for future sessions. Call this when the user explicitly states a preference (e.g. 'I prefer playful style', 'always use Azure voice'). Only send fields that should be updated — existing fields are preserved.

Analyze a YouTube video and generate a structured course outline. Extracts the transcript (or uses video analysis as fallback) and reorganizes it into a teaching outline. Cost: min 30 credits, actual = max(30, ceil(video_duration_minutes) x 2). A 5-min video costs 30 credits,...