hermoso 0.1.35 → 0.1.38

package/mcp/tools.mjs

@@ -4454,8 +4454,8 @@ export function registerTools(server) {
       style: z.enum(['cinematic', 'editorial_collage', 'flat_vector', 'stickman', 'whiteboard', 'ink_marker', 'silhouette', 'storybook', 'paper_diorama', 'isometric', 'claymation', 'pixel_art', 'watercolor', 'fluffy_toy', 'low_poly', 'stylized_3d', 'studio_3d', 'mannequin']).optional().describe("visual style. 'cinematic' (default) is photoreal; the rest are non-photoreal styled looks — editorial_collage (halftone cutouts + marker accents), flat_vector, stickman, whiteboard, ink_marker, silhouette, storybook (gouache), paper_diorama, isometric, claymation, pixel_art, watercolor, fluffy_toy (felted plush), low_poly, stylized_3d (matte clay render), studio_3d (preschool toy 3D on a white sweep — the Kids default), mannequin (clay-render reenactment figures — a History alternate). Ask the user which they want rather than picking silently; a styled pick costs more (see the cost note)."),
       channel: z.enum(['explainer', 'history', 'kids', 'fairytale']).optional().describe("the CHANNEL TYPE — it sets the pacing, the narration register and the default look, and is orthogonal to `style` (a named style always wins): explainer (casual second-person, fast cuts), history (witty chronological retelling / documentary), kids (fastest, question-first, warm teacher), fairytale (slow, atmospheric myth or folklore). Default 'explainer'."),
       voice: z.string().optional().describe('narration voice name — omit for the default warm read'),
-      captions: z.boolean().optional().describe('burn ON-SCREEN KEY POINTS — one short line per section (at most 5 words / 32 characters, enforced), held over the picture for that whole section (~7-15s). Drawn by the same burner the subtitles use: slim white CAPS, thin black outline, bottom safe band, NO plate and no box. DEFAULT FALSE: the narration already says the point and the pictures carry it, so the clean film is the better default. Set true only when the user asks for on-screen text.'),
-      subtitles: z.boolean().optional().describe('burn CAPS SUBTITLES timed to the narration instead of the held key points (default false; implies captions). Free — no extra render, no extra credits, and there is NO cue limit: the whole film is subtitled however long it runs. Slim white CAPS, thin black outline, bottom safe band, no plate, at most 5 words / 32 characters per line. TIMING: each cue is anchored to that section’s REAL measured narration length and distributed inside the section by character count — exact at every section boundary, approximate to a few tenths of a second within one. It is not a word-level speech clock, so never promise frame-accurate sync.'),
+      captions: z.boolean().optional().describe('turn ON-SCREEN TEXT on. DEFAULT FALSE, and leave it false unless the user asks — the narration already says the point and the pictures carry it, so the clean film is the better default. `captions:true` on its own burns SUBTITLES (see below), because that is what a caption is for: showing what is being said when the phone is on mute. Slim white CAPS, thin black outline, bottom safe band, no plate, no box.'),
+      subtitles: z.boolean().optional().describe('which on-screen text, once `captions` is on. LEAVE IT UNSET (or true) for SUBTITLES — every spoken word, in order, timed to the narration; free, no extra render, no extra credits, and there is NO cue limit, so the whole film is subtitled however long it runs (at most 5 words / 32 characters a line). Set it FALSE only if the user explicitly wants section HEADINGS instead: one short summary label held over each ~7-15s section. That is NOT what is being said — it is a label about it — so it is the wrong answer to "add captions" and to anyone watching on mute. `subtitles:true` also implies `captions:true`. TIMING: each cue is anchored to that section’s REAL measured narration length and distributed inside the section by character count — exact at every section boundary, approximate to a few tenths of a second within one. It is not a word-level speech clock, so never promise frame-accurate sync.'),
       music: z.string().optional().describe("music bed under the narration, measured to sit about 14 dB under the voice and sidechain-ducked beneath it. Omit and the KIDS and FAIRYTALE channels get their recommended bed COMPOSED for this film — those two are the only channels a bed is due on unasked, and it costs a small flat fee; every other channel ships dry. 'off' forces silence. 'library' takes a free curated track only, and ships dry when none is on file. NAME A MOOD — upbeat / calm / warm / epic / tense / playful / elegant / hype / chill / dramatic — to compose one on ANY channel, at the same fee. hermoso_capabilities reports the exact figure as explainerMusicCredits; quote it before you turn a bed on or pick a mood."),
       upscale: z.number().optional().describe("optional FINAL upscale — 2 doubles each side, 4 quadruples. Captions and the end card are burned BEFORE it so they upscale with the frame. It is priced BY LENGTH and it is the expensive part — several times the cost of rendering the film itself. hermoso_capabilities reports the exact figures per length as explainerUpscaleCredits. Never turn it on unasked: quote the number and let the user choose."),
       endCard: z.boolean().optional().describe('append the branded end card (default true)'),

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "hermoso",
-  "version": "0.1.35",
+  "version": "0.1.38",
   "mcpName": "io.github.hermoso-ai/hermoso",
   "description": "Generate finished VIDEO ADS, image ads and UGC avatar ads for any brand with AI — spy on competitor ads across the Meta, Google and LinkedIn ad libraries plus TikTok/Instagram/YouTube organic — then publish to Facebook, Instagram, Threads, TikTok, YouTube, X, LinkedIn and Pinterest and build & manage the ad campaigns behind them on Meta, Google Ads, LinkedIn, Pinterest, Microsoft Advertising and ChatGPT Ads. MCP server (262 tools), CLI and Claude skills for Hermoso, the AI ad studio: brand onboarding, 30+ image/video models, finished-ad pipeline (script, voiceover, music, brand end card), ad scoring and competitor teardowns.",
   "type": "module",