mulmocast 1.1.9 → 1.1.11

package/lib/actions/audio.js

@@ -1,19 +1,14 @@
 import "dotenv/config";
 import { GraphAI, TaskManager } from "graphai";
 import * as agents from "@graphai/vanilla";
-import ttsNijivoiceAgent from "../agents/tts_nijivoice_agent.js";
-import addBGMAgent from "../agents/add_bgm_agent.js";
-import combineAudioFilesAgent from "../agents/combine_audio_files_agent.js";
-import ttsOpenaiAgent from "../agents/tts_openai_agent.js";
-import ttsGoogleAgent from "../agents/tts_google_agent.js";
-import ttsElevenlabsAgent from "../agents/tts_elevenlabs_agent.js";
 import { fileWriteAgent } from "@graphai/vanilla_node_agents";
-import { MulmoPresentationStyleMethods } from "../methods/index.js";
+import { ttsNijivoiceAgent, ttsOpenaiAgent, ttsGoogleAgent, ttsElevenlabsAgent, addBGMAgent, combineAudioFilesAgent, mediaMockAgent } from "../agents/index.js";
 import { text2SpeechProviderSchema } from "../types/index.js";
 import { fileCacheAgentFilter, nijovoiceTextAgentFilter } from "../utils/filters.js";
 import { getAudioArtifactFilePath, getAudioFilePath, getOutputStudioFilePath, resolveDirPath, defaultBGMPath, mkdir, writingMessage } from "../utils/file.js";
 import { text2hash, localizedText, settings2GraphAIConfig } from "../utils/utils.js";
 import { provider2TTSAgent } from "../utils/provider2agent.js";
+import { MulmoPresentationStyleMethods } from "../methods/index.js";
 import { MulmoStudioContextMethods } from "../methods/mulmo_studio_context.js";
 import { MulmoMediaSourceMethods } from "../methods/mulmo_media_source.js";
 const vanillaAgents = agents.default ?? agents;
@@ -85,6 +80,7 @@ const graph_tts = {
             if: ":preprocessor.needsTTS",
             agent: ":preprocessor.ttsAgent",
             inputs: {
+                media: "audio",
                 text: ":preprocessor.text",
                 provider: ":preprocessor.provider",
                 lang: ":preprocessor.lang",
@@ -146,7 +142,6 @@ const graph_data = {
         },
         addBGM: {
             agent: "addBGMAgent",
-            unless: ":context.presentationStyle.audioParams.bgmVolume.equal(0)",
             inputs: {
                 wait: ":combineFiles",
                 voiceFile: ":audioCombinedFilePath",
@@ -156,18 +151,6 @@ const graph_data = {
                     musicFile: ":musicFile",
                 },
             },
-            isResult: true,
-            defaultValue: {},
-        },
-        title: {
-            agent: "copyAgent",
-            params: {
-                namedKey: "title",
-            },
-            inputs: {
-                title: "\n${:context.studio.script.title}\n\n${:context.studio.script.description}\nReference: ${:context.studio.script.reference}\n",
-                waitFor: ":addBGM",
-            },
         },
     },
 };
@@ -198,6 +181,7 @@ const audioAgents = {
     ttsNijivoiceAgent,
     ttsGoogleAgent,
     ttsElevenlabsAgent,
+    mediaMockAgent,
     addBGMAgent,
     combineAudioFilesAgent,
 };

package/lib/actions/image_references.js

@@ -4,7 +4,7 @@ import { getReferenceImagePath } from "../utils/file.js";
 import { getExtention } from "../utils/utils.js";
 import { graphOption } from "./images.js";
 import { MulmoPresentationStyleMethods, MulmoStudioContextMethods } from "../methods/index.js";
-import { imageGoogleAgent, imageOpenaiAgent } from "../agents/index.js";
+import { imageGoogleAgent, imageOpenaiAgent, mediaMockAgent } from "../agents/index.js";
 // public api
 // Application may call this function directly to generate reference image.
 export const generateReferenceImage = async (inputs) => {
@@ -21,6 +21,7 @@ export const generateReferenceImage = async (inputs) => {
                 agent: imageAgentInfo.agent,
                 retry: 2,
                 inputs: {
+                    media: "image",
                     prompt,
                     cache: {
                         force: [context.force, force ?? false],
@@ -38,7 +39,7 @@ export const generateReferenceImage = async (inputs) => {
         },
     };
     const options = await graphOption(context);
-    const graph = new GraphAI(image_graph_data, { imageGoogleAgent, imageOpenaiAgent }, options);
+    const graph = new GraphAI(image_graph_data, { imageGoogleAgent, imageOpenaiAgent, mediaMockAgent }, options);
     await graph.run();
     return imagePath;
 };

package/lib/actions/images.js

@@ -22,6 +22,7 @@ const imageAgents = {
 const movieAgents = {
     movieGoogleAgent,
     movieReplicateAgent,
+    mediaMockAgent,
 };
 const soundEffectAgents = {
     soundEffectReplicateAgent,
@@ -77,6 +78,7 @@ const beat_graph_data = {
             defaultValue: {},
             agent: ":htmlImageAgentInfo.agent",
             inputs: {
+                media: "html",
                 prompt: ":preprocessor.htmlPrompt",
                 system: ":preprocessor.htmlImageSystemPrompt",
                 params: {
@@ -122,6 +124,7 @@ const beat_graph_data = {
             agent: ":preprocessor.imageAgentInfo.agent",
             retry: 2,
             inputs: {
+                media: "image",
                 prompt: ":preprocessor.prompt",
                 referenceImages: ":preprocessor.referenceImages",
                 cache: {
@@ -144,6 +147,7 @@ const beat_graph_data = {
             if: ":preprocessor.movieFile",
             agent: ":preprocessor.movieAgentInfo.agent",
             inputs: {
+                media: "movie",
                 onComplete: [":imageGenerator", ":imagePlugin"], // to wait for imageGenerator to finish
                 prompt: ":beat.moviePrompt",
                 imagePath: ":preprocessor.referenceImageForMovie",

package/lib/actions/translate.d.ts

@@ -46,6 +46,10 @@ export declare const translateTextGraph: {
         };
     };
 };
+export declare const getOutputMultilingualFilePathAndMkdir: (context: MulmoStudioContext) => {
+    outputMultilingualFilePath: string;
+    outDirPath: string;
+};
 export declare const translateBeat: (index: number, context: MulmoStudioContext, targetLangs: string[], args?: {
     settings?: Record<string, string>;
     callbacks?: CallbackFunction[];

package/lib/actions/translate.js

@@ -1,5 +1,4 @@
 import "dotenv/config";
-import { createHash } from "crypto";
 import fs from "fs";
 import { GraphAI, assert, isNull, GraphAILogger } from "graphai";
 import * as agents from "@graphai/vanilla";
@@ -9,13 +8,10 @@ import { splitText } from "../utils/string.js";
 import { settings2GraphAIConfig } from "../utils/utils.js";
 import { getMultiLingual } from "../utils/context.js";
 import { currentMulmoScriptVersion } from "../utils/const.js";
-import { getOutputMultilingualFilePath, mkdir, writingMessage } from "../utils/file.js";
+import { getOutputMultilingualFilePath, mkdir, writingMessage, hashSHA256 } from "../utils/file.js";
 import { translateSystemPrompt, translatePrompts } from "../utils/prompt.js";
 import { MulmoStudioContextMethods } from "../methods/mulmo_studio_context.js";
 const vanillaAgents = agents.default ?? agents;
-const hashSHA256 = (text) => {
-    return createHash("sha256").update(text, "utf8").digest("hex");
-};
 // 1. translateGraph / map each beats.
 // 2. beatGraph / map each target lang.
 // 3. translateTextGraph / translate text.
@@ -202,6 +198,13 @@ const agentFilters = [
         nodeIds: ["localizedText"],
     },
 ];
+export const getOutputMultilingualFilePathAndMkdir = (context) => {
+    const fileName = MulmoStudioContextMethods.getFileName(context);
+    const outDirPath = MulmoStudioContextMethods.getOutDirPath(context);
+    const outputMultilingualFilePath = getOutputMultilingualFilePath(outDirPath, fileName);
+    mkdir(outDirPath);
+    return { outputMultilingualFilePath, outDirPath };
+};
 export const translateBeat = async (index, context, targetLangs, args) => {
     const { settings, callbacks } = args ?? {};
     // Validate inputs
@@ -212,10 +215,7 @@ export const translateBeat = async (index, context, targetLangs, args) => {
         throw new Error("targetLangs must be a non-empty array");
     }
     try {
-        const fileName = MulmoStudioContextMethods.getFileName(context);
-        const outDirPath = MulmoStudioContextMethods.getOutDirPath(context);
-        const outputMultilingualFilePath = getOutputMultilingualFilePath(outDirPath, fileName);
-        mkdir(outDirPath);
+        const { outputMultilingualFilePath } = getOutputMultilingualFilePathAndMkdir(context);
         const config = settings2GraphAIConfig(settings, process.env);
         assert(!!config?.openAIAgent?.apiKey, "The OPENAI_API_KEY environment variable is missing or empty");
         const graph = new GraphAI(beatGraph, { ...vanillaAgents, fileWriteAgent, openAIAgent }, { agentFilters, config });
@@ -246,10 +246,7 @@ export const translate = async (context, args) => {
     const { settings, callbacks } = args ?? {};
     try {
         MulmoStudioContextMethods.setSessionState(context, "multiLingual", true);
-        const fileName = MulmoStudioContextMethods.getFileName(context);
-        const outDirPath = MulmoStudioContextMethods.getOutDirPath(context);
-        const outputMultilingualFilePath = getOutputMultilingualFilePath(outDirPath, fileName);
-        mkdir(outDirPath);
+        const { outputMultilingualFilePath, outDirPath } = getOutputMultilingualFilePathAndMkdir(context);
         const targetLangs = [...new Set([context.lang, context.studio.script.captionParams?.lang].filter((x) => !isNull(x)))];
         const config = settings2GraphAIConfig(settings, process.env);
         assert(!!config?.openAIAgent?.apiKey, "The OPENAI_API_KEY environment variable is missing or empty");

package/lib/agents/index.d.ts

@@ -9,6 +9,7 @@ import mediaMockAgent from "./media_mock_agent.js";
 import ttsElevenlabsAgent from "./tts_elevenlabs_agent.js";
 import ttsNijivoiceAgent from "./tts_nijivoice_agent.js";
 import ttsOpenaiAgent from "./tts_openai_agent.js";
+import ttsGoogleAgent from "./tts_google_agent.js";
 import validateSchemaAgent from "./validate_schema_agent.js";
 import soundEffectReplicateAgent from "./sound_effect_replicate_agent.js";
 import lipSyncReplicateAgent from "./lipsync_replicate_agent.js";
@@ -16,4 +17,4 @@ import { browserlessAgent } from "@graphai/browserless_agent";
 import { textInputAgent } from "@graphai/input_agents";
 import { openAIAgent } from "@graphai/openai_agent";
 import { fileWriteAgent } from "@graphai/vanilla_node_agents";
-export { openAIAgent, fileWriteAgent, browserlessAgent, textInputAgent, addBGMAgent, combineAudioFilesAgent, imageGoogleAgent, imageOpenaiAgent, tavilySearchAgent, movieGoogleAgent, movieReplicateAgent, mediaMockAgent, ttsElevenlabsAgent, ttsNijivoiceAgent, ttsOpenaiAgent, validateSchemaAgent, soundEffectReplicateAgent, lipSyncReplicateAgent, };
+export { openAIAgent, fileWriteAgent, browserlessAgent, textInputAgent, addBGMAgent, combineAudioFilesAgent, imageGoogleAgent, imageOpenaiAgent, tavilySearchAgent, movieGoogleAgent, movieReplicateAgent, mediaMockAgent, ttsElevenlabsAgent, ttsNijivoiceAgent, ttsOpenaiAgent, ttsGoogleAgent, validateSchemaAgent, soundEffectReplicateAgent, lipSyncReplicateAgent, };

package/lib/agents/index.js

@@ -9,6 +9,7 @@ import mediaMockAgent from "./media_mock_agent.js";
 import ttsElevenlabsAgent from "./tts_elevenlabs_agent.js";
 import ttsNijivoiceAgent from "./tts_nijivoice_agent.js";
 import ttsOpenaiAgent from "./tts_openai_agent.js";
+import ttsGoogleAgent from "./tts_google_agent.js";
 import validateSchemaAgent from "./validate_schema_agent.js";
 import soundEffectReplicateAgent from "./sound_effect_replicate_agent.js";
 import lipSyncReplicateAgent from "./lipsync_replicate_agent.js";
@@ -17,4 +18,4 @@ import { textInputAgent } from "@graphai/input_agents";
 import { openAIAgent } from "@graphai/openai_agent";
 // import * as vanilla from "@graphai/vanilla";
 import { fileWriteAgent } from "@graphai/vanilla_node_agents";
-export { openAIAgent, fileWriteAgent, browserlessAgent, textInputAgent, addBGMAgent, combineAudioFilesAgent, imageGoogleAgent, imageOpenaiAgent, tavilySearchAgent, movieGoogleAgent, movieReplicateAgent, mediaMockAgent, ttsElevenlabsAgent, ttsNijivoiceAgent, ttsOpenaiAgent, validateSchemaAgent, soundEffectReplicateAgent, lipSyncReplicateAgent, };
+export { openAIAgent, fileWriteAgent, browserlessAgent, textInputAgent, addBGMAgent, combineAudioFilesAgent, imageGoogleAgent, imageOpenaiAgent, tavilySearchAgent, movieGoogleAgent, movieReplicateAgent, mediaMockAgent, ttsElevenlabsAgent, ttsNijivoiceAgent, ttsOpenaiAgent, ttsGoogleAgent, validateSchemaAgent, soundEffectReplicateAgent, lipSyncReplicateAgent, };

package/lib/agents/media_mock_agent.js

@@ -1,5 +1,28 @@
 import { GraphAILogger } from "graphai";
-export const mediaMockAgent = async () => {
+import fs from "fs";
+import { silent60secPath, mulmoCreditPath } from "../utils/file.js";
+export const mediaMockAgent = async ({ namedInputs }) => {
+    if (namedInputs.media === "audio") {
+        const buffer = fs.readFileSync(silent60secPath());
+        return { buffer };
+    }
+    if (namedInputs.media === "image") {
+        const buffer = fs.readFileSync(mulmoCreditPath());
+        return { buffer };
+    }
+    if (namedInputs.media === "movie") {
+        const url = "https://github.com/receptron/mulmocast-media/raw/refs/heads/main/test/pingpong.mov";
+        const res = await fetch(url);
+        if (!res.ok) {
+            throw new Error(`Failed to fetch: ${res.status} ${res.statusText}`);
+        }
+        const arrayBuffer = await res.arrayBuffer();
+        const buffer = Buffer.from(arrayBuffer);
+        return { buffer };
+    }
+    if (namedInputs.media === "html") {
+        return { text: "<html><title>test</title><body>test</body></html>" };
+    }
     GraphAILogger.debug("agent dryRun");
     return { buffer: Buffer.from([]) };
 };

package/lib/cli/commands/tool/scripting/builder.d.ts

@@ -16,7 +16,7 @@ export declare const builder: (yargs: Argv) => Argv<{
 } & {
     s: string;
 } & {
-    llm: "openai" | "anthropic" | "gemini" | "groq" | undefined;
+    llm: "mock" | "openai" | "anthropic" | "gemini" | "groq" | undefined;
 } & {
     llm_model: string | undefined;
 }>;

package/lib/cli/commands/tool/story_to_script/builder.d.ts

@@ -10,7 +10,7 @@ export declare const builder: (yargs: Argv) => Argv<{
 } & {
     beats_per_scene: number;
 } & {
-    llm: "openai" | "anthropic" | "gemini" | "groq" | undefined;
+    llm: "mock" | "openai" | "anthropic" | "gemini" | "groq" | undefined;
 } & {
     llm_model: string | undefined;
 } & {

package/lib/methods/mulmo_script.js

@@ -1,3 +1,4 @@
+import { GraphAILogger } from "graphai";
 import { mulmoScriptSchema, mulmoStudioMultiLingualFileSchema } from "../types/index.js";
 // eslint-disable-next-line @typescript-eslint/no-explicit-any
 const validate_1_0 = (script) => {
@@ -37,6 +38,9 @@ export const MulmoStudioMultiLingualMethod = {
     validate(jsonData, studioBeatsLength) {
         // TODO version check
         const result = mulmoStudioMultiLingualFileSchema.safeParse(jsonData);
+        if (!result.success) {
+            GraphAILogger.warn("multiLingual file validation failed.");
+        }
         const dataSet = result.success ? result.data.multiLingual : [];
         while (dataSet.length < studioBeatsLength) {
             dataSet.push({ multiLingualTexts: {} });

package/lib/utils/file.d.ts

@@ -37,6 +37,7 @@ export declare const getPromptTemplateFilePath: (promptTemplateName: string) =>
 export declare const mkdir: (dirPath: string) => void;
 export declare const silent60secPath: () => string;
 export declare const defaultBGMPath: () => string;
+export declare const mulmoCreditPath: () => string;
 export declare const getHTMLFile: (filename: string) => string;
 export declare const getBaseDirPath: (basedir?: string) => string;
 export declare const getFullPath: (baseDirPath: string | undefined, file: string) => string;
@@ -48,3 +49,4 @@ export declare const getAvailableScriptTemplates: () => MulmoScript[];
 export declare const writingMessage: (filePath: string) => void;
 export declare const readAndParseJson: <S extends ZodSchema<any>>(filePath: string, schema: S) => ReturnType<S["parse"]>;
 export declare const generateTimestampedFileName: (prefix: string) => string;
+export declare const hashSHA256: (text: string) => string;

package/lib/utils/file.js

@@ -1,5 +1,6 @@
 import fs from "fs";
 import path from "path";
+import { createHash } from "crypto";
 import { parse as yamlParse } from "yaml";
 import { fileURLToPath } from "url";
 import { GraphAILogger } from "graphai";
@@ -131,6 +132,7 @@ export const mkdir = (dirPath) => {
 // export const silentLastPath = path.resolve(npmRoot, "./assets/audio/silent800.mp3");
 export const silent60secPath = () => path.resolve(npmRoot, "./assets/audio/silent60sec.mp3");
 export const defaultBGMPath = () => "https://github.com/receptron/mulmocast-media/raw/refs/heads/main/bgms/story002.mp3";
+export const mulmoCreditPath = () => path.resolve(npmRoot, "./assets/images/mulmocast_credit.png");
 export const getHTMLFile = (filename) => {
     const htmlPath = path.resolve(npmRoot, `./assets/html/${filename}.html`);
     return fs.readFileSync(htmlPath, "utf-8");
@@ -226,3 +228,6 @@ export const generateTimestampedFileName = (prefix) => {
     const pad = (n) => n.toString().padStart(2, "0");
     return `${prefix}_${now.getFullYear()}${pad(now.getMonth() + 1)}${pad(now.getDate())}_${pad(now.getHours())}${pad(now.getMinutes())}${pad(now.getSeconds())}`;
 };
+export const hashSHA256 = (text) => {
+    return createHash("sha256").update(text, "utf8").digest("hex");
+};

package/lib/utils/provider2agent.d.ts

@@ -19,6 +19,12 @@ export declare const provider2TTSAgent: {
         defaultModel: string;
         models: string[];
     };
+    mock: {
+        agentName: string;
+        hasLimitedConcurrency: boolean;
+        defaultModel: string;
+        models: string[];
+    };
 };
 export declare const provider2ImageAgent: {
     openai: {
@@ -31,6 +37,11 @@ export declare const provider2ImageAgent: {
         defaultModel: string;
         models: string[];
     };
+    mock: {
+        agentName: string;
+        defaultModel: string;
+        models: string[];
+    };
 };
 export type ReplicateModel = `${string}/${string}`;
 export declare const provider2MovieAgent: {
@@ -50,6 +61,11 @@ export declare const provider2MovieAgent: {
         defaultModel: string;
         models: string[];
     };
+    mock: {
+        agentName: string;
+        defaultModel: string;
+        models: string[];
+    };
 };
 export declare const provider2SoundEffectAgent: {
     replicate: {
@@ -95,6 +111,11 @@ export declare const provider2LLMAgent: {
         readonly defaultModel: "llama3-8b-8192";
         readonly max_tokens: 4096;
     };
+    readonly mock: {
+        readonly agentName: "mediaMockAgent";
+        readonly defaultModel: "mock";
+        readonly max_tokens: 4096;
+    };
 };
 export declare const defaultProviders: {
     tts: keyof typeof provider2TTSAgent;

package/lib/utils/provider2agent.js

@@ -22,6 +22,12 @@ export const provider2TTSAgent = {
         // https://elevenlabs.io/docs/models
         models: ["eleven_multilingual_v2", "eleven_turbo_v2_5", "eleven_turbo_v2", "eleven_flash_v2_5", "eleven_flash_v2"],
     },
+    mock: {
+        agentName: "mediaMockAgent",
+        hasLimitedConcurrency: true,
+        defaultModel: "mock-model",
+        models: ["mock-model"],
+    },
 };
 export const provider2ImageAgent = {
     openai: {
@@ -34,6 +40,11 @@ export const provider2ImageAgent = {
         defaultModel: "imagen-3.0-fast-generate-001",
         models: ["imagen-3.0-fast-generate-001", "imagen-3.0-generate-002", "imagen-3.0-capability-001"],
     },
+    mock: {
+        agentName: "mediaMockAgent",
+        defaultModel: "mock-model",
+        models: ["mock-model"],
+    },
 };
 export const provider2MovieAgent = {
     replicate: {
@@ -50,6 +61,7 @@ export const provider2MovieAgent = {
             "google/veo-3-fast",
             "minimax/video-01",
             "minimax/hailuo-02",
+            "minimax/hailuo-02-fast",
             "pixverse/pixverse-v4.5",
             "wan-video/wan-2.2-i2v-480p-fast",
             "wan-video/wan-2.2-t2v-480p-fast",
@@ -89,12 +101,12 @@ export const provider2MovieAgent = {
             },
             "google/veo-3": {
                 durations: [8],
-                start_image: undefined,
+                start_image: "image",
                 price_per_sec: 0.75,
             },
             "google/veo-3-fast": {
                 durations: [8],
-                start_image: undefined,
+                start_image: "image",
                 price_per_sec: 0.4,
             },
             "minimax/video-01": {
@@ -107,6 +119,11 @@ export const provider2MovieAgent = {
                 start_image: "first_frame_image",
                 price_per_sec: 0.08,
             },
+            "minimax/hailuo-02-fast": {
+                durations: [6, 10], // NOTE: 512P
+                start_image: "first_frame_image",
+                price_per_sec: 0.0166,
+            },
             "pixverse/pixverse-v4.5": {
                 durations: [5, 8],
                 start_image: "image",
@@ -130,6 +147,11 @@ export const provider2MovieAgent = {
         defaultModel: "veo-2.0-generate-001",
         models: ["veo-2.0-generate-001"],
     },
+    mock: {
+        agentName: "mediaMockAgent",
+        defaultModel: "mock-model",
+        models: ["mock-model"],
+    },
 };
 export const provider2SoundEffectAgent = {
     replicate: {
@@ -202,6 +224,11 @@ export const provider2LLMAgent = {
         defaultModel: "llama3-8b-8192",
         max_tokens: 4096,
     },
+    mock: {
+        agentName: "mediaMockAgent",
+        defaultModel: "mock",
+        max_tokens: 4096,
+    },
 };
 export const defaultProviders = {
     tts: "openai",
@@ -213,4 +240,4 @@ export const defaultProviders = {
     lipSync: "replicate",
 };
 export const llm = Object.keys(provider2LLMAgent);
-export const htmlLLMProvider = ["openai", "anthropic"];
+export const htmlLLMProvider = ["openai", "anthropic", "mock"];

package/lib/utils/string.js

@@ -46,6 +46,7 @@ export const replacementsJa = [
     { from: "Groq", to: "グロック" },
     { from: "TSMC", to: "ティーエスエムシー" },
     { from: "NVIDIA", to: "エヌビディア" },
+    { from: "PER", to: "ピーイーアール" },
     { from: "1つ", to: "ひとつ" },
     { from: "2つ", to: "ふたつ" },
     { from: "3つ", to: "みっつ" },

package/lib/utils/utils.d.ts

@@ -2,7 +2,7 @@ import type { ConfigDataDictionary, DefaultConfigData } from "graphai";
 import { MulmoBeat, MulmoStudioMultiLingualData } from "../types/index.js";
 import type { LLM } from "./provider2agent.js";
 export declare const llmPair: (_llm?: LLM, _model?: string) => {
-    agent: "openAIAgent" | "anthropicAgent" | "geminiAgent" | "groqAgent";
+    agent: "mediaMockAgent" | "openAIAgent" | "anthropicAgent" | "geminiAgent" | "groqAgent";
     model: string;
     max_tokens: 8192 | 4096;
 };

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "mulmocast",
-  "version": "1.1.9",
+  "version": "1.1.11",
   "description": "",
   "type": "module",
   "main": "lib/index.node.js",
@@ -26,6 +26,7 @@
     "./scripts/test",
     "./assets/audio/silent60sec.mp3",
     "./assets/html/",
+    "./assets/images/",
     "./assets/templates/"
   ],
   "directories": {
@@ -82,8 +83,8 @@
     "fluent-ffmpeg": "^2.1.3",
     "google-auth-library": "^10.1.0",
     "graphai": "^2.0.13",
-    "inquirer": "^12.7.0",
-    "marked": "^16.1.1",
+    "inquirer": "^12.9.0",
+    "marked": "^16.1.2",
     "ora": "^8.2.0",
     "puppeteer": "^24.15.0",
     "replicate": "^1.0.1",
@@ -106,7 +107,7 @@
     "ts-node": "^10.9.2",
     "tsx": "^4.20.3",
     "typescript": "^5.9.2",
-    "typescript-eslint": "^8.37.0"
+    "typescript-eslint": "^8.39.0"
   },
   "engines": {
     "node": ">=18.0.0"

package/scripts/test/test_hello_bgm_0.json

@@ -0,0 +1,21 @@
+{
+  "$mulmocast": {
+    "version": "1.1"
+  },
+  "audioParams": {
+    "bgmVolume": 0
+  },
+  "lang": "en",
+  "beats": [
+    {
+      "text": "Hello World",
+      "image": {
+        "type": "textSlide",
+        "slide": {
+          "title": "Hello World",
+          "bullets": ["Hello", "World"]
+        }
+      }
+    }
+  ]
+}

package/scripts/test/test_hello_caption.json

@@ -0,0 +1,38 @@
+{
+  "$mulmocast": {
+    "version": "1.1"
+  },
+  "lang": "en",
+  "captionParams": {
+    "lang": "en"
+  },
+  "movieParams": {
+    "provider": "mock"
+  },
+  "speechParams": {
+    "speakers": {
+      "Presenter": {
+        "displayName": {
+          "en": "Presenter"
+        },
+        "voiceId": "ae42d8b0-0c4b-4289-95b7-cf988569af36",
+        "provider": "mock"
+      }
+    }
+  },
+  "imageParams": {
+    "provider": "mock"
+  },
+  "beats": [
+    {
+      "text": "Hello World",
+      "image": {
+        "type": "textSlide",
+        "slide": {
+          "title": "Hello World",
+          "bullets": ["Hello", "World"]
+        }
+      }
+    }
+  ]
+}

package/scripts/test/test_hello_caption.json~

@@ -0,0 +1,21 @@
+{
+  "$mulmocast": {
+    "version": "1.1"
+  },
+  "lang": "en",
+  "captionParams": {
+    "lang": "en"
+  },
+  "beats": [
+    {
+      "text": "Hello World",
+      "image": {
+        "type": "textSlide",
+        "slide": {
+          "title": "Hello World",
+          "bullets": ["Hello", "World"]
+        }
+      }
+    }
+  ]
+}

package/scripts/test/test_hello_image.json

@@ -0,0 +1,42 @@
+{
+  "$mulmocast": {
+    "version": "1.1"
+  },
+  "lang": "en",
+  "movieParams": {
+    "provider": "mock"
+  },
+  "speechParams": {
+    "speakers": {
+      "Presenter": {
+        "displayName": {
+          "en": "Presenter"
+        },
+        "voiceId": "ae42d8b0-0c4b-4289-95b7-cf988569af36",
+        "provider": "mock"
+      }
+    }
+  },
+  "htmlImageParams": {
+    "provider": "mock"
+  },
+  "imageParams": {
+    "provider": "mock"
+  },
+  "beats": [
+    {
+      "text": "Hello World"
+    },
+    {
+      "text": "Hello World",
+      "moviePrompt": "fire"
+    },
+    {
+      "text": "Hello World",
+      "htmlPrompt": {
+        "prompt": "fire",
+        "data": []
+      }
+    }
+  ]
+}

package/scripts/test/test_hello_image.json~

@@ -0,0 +1,18 @@
+{
+  "$mulmocast": {
+    "version": "1.1"
+  },
+  "lang": "en",
+  "beats": [
+    {
+      "text": "Hello World",
+      "image": {
+        "type": "textSlide",
+        "slide": {
+          "title": "Hello World",
+          "bullets": ["Hello", "World"]
+        }
+      }
+    }
+  ]
+}

package/scripts/test/test_hello_nobgm.json

@@ -0,0 +1,21 @@
+{
+  "$mulmocast": {
+    "version": "1.1"
+  },
+  "lang": "en",
+  "audioParams": {
+    "bgmVolume": 0
+  },
+  "beats": [
+    {
+      "text": "Hello World",
+      "image": {
+        "type": "textSlide",
+        "slide": {
+          "title": "Hello World",
+          "bullets": ["Hello", "World"]
+        }
+      }
+    }
+  ]
+}

package/scripts/test/test_replicate.json

@@ -48,6 +48,16 @@
         "model": "google/veo-3-fast"
       }
     },
+    {
+      "id": "veo-3-fast with a start image",
+      "text": "google/veo-3-fast with a start image",
+      "duration": 8,
+      "imagePrompt": "a woman is walking through a busy Tokyo street at night, she is wearing dark sunglasses",
+      "moviePrompt": "a woman is walking through a busy Tokyo street at night, she is wearing dark sunglasses",
+      "movieParams": {
+        "model": "google/veo-3-fast"
+      }
+    },
     {
       "id": "seedance-1-lite",
       "text": "bytedance seedance-1-lite",
@@ -114,7 +124,7 @@
     },
     {
       "id": "hailuo-02-image",
-      "text": "minimax/hailuo-02 with ghibli-styleimage",
+      "text": "minimax/hailuo-02 with start image",
       "duration": 6,
       "imagePrompt": "a cat is doing an acrobatic dive into a swimming pool at the olympics, from a 10m high diving board, Ghibli style",
       "moviePrompt": "televised footage of a cat is doing an acrobatic dive into a swimming pool at the olympics, from a 10m high diving board, flips and spins",
@@ -122,6 +132,16 @@
         "model": "minimax/hailuo-02"
       }
     },
+    {
+      "id": "hailuo-02-fast",
+      "text": "minimax/hailuo-02-fast with no start image",
+      "duration": 10,
+      "imagePrompt": "televised footage of a cat preparing to dive into a swimming pool at the olympics, from a 10m high diving board",
+      "moviePrompt": "a cat is doing an acrobatic dive into a swimming pool at the olympics, from a 10m high diving board, flips and spins",
+      "movieParams": {
+        "model": "minimax/hailuo-02-fast"
+      }
+    },
     {
       "id": "wan-2.2-i2v-480p-fast",
       "text": "wan-video/wan-2.2-i2v-480p-fast",