mulmocast 2.0.8 → 2.1.0

package/lib/types/type.d.ts

@@ -1,5 +1,5 @@
 import { type CallbackFunction } from "graphai";
-import { langSchema, localizedTextSchema, mulmoBeatSchema, mulmoScriptSchema, mulmoStudioSchema, mulmoStudioBeatSchema, mulmoStoryboardSchema, mulmoStoryboardSceneSchema, mulmoStudioMultiLingualSchema, mulmoStudioMultiLingualArraySchema, mulmoStudioMultiLingualDataSchema, mulmoStudioMultiLingualFileSchema, speakerDictionarySchema, speakerSchema, mulmoSpeechParamsSchema, mulmoImageParamsSchema, mulmoImageParamsImagesValueSchema, mulmoImageParamsImagesSchema, mulmoFillOptionSchema, mulmoMovieParamsSchema, mulmoSoundEffectParamsSchema, mulmoLipSyncParamsSchema, textSlideParamsSchema, speechOptionsSchema, speakerDataSchema, mulmoCanvasDimensionSchema, mulmoPromptTemplateSchema, mulmoPromptTemplateFileSchema, text2ImageProviderSchema, text2HtmlImageProviderSchema, text2MovieProviderSchema, text2SpeechProviderSchema, mulmoPresentationStyleSchema, multiLingualTextsSchema, mulmoImageAssetSchema, mulmoMermaidMediaSchema, mulmoTextSlideMediaSchema, mulmoMarkdownMediaSchema, mulmoImageMediaSchema, mulmoChartMediaSchema, mediaSourceSchema, mediaSourceMermaidSchema, mulmoSessionStateSchema, mulmoOpenAIImageModelSchema, mulmoGoogleImageModelSchema, mulmoGoogleMovieModelSchema, mulmoReplicateMovieModelSchema, mulmoImagePromptMediaSchema } from "./schema.js";
+import { langSchema, localizedTextSchema, mulmoBeatSchema, mulmoScriptSchema, mulmoStudioSchema, mulmoStudioBeatSchema, mulmoStoryboardSchema, mulmoStoryboardSceneSchema, mulmoStudioMultiLingualSchema, mulmoStudioMultiLingualArraySchema, mulmoStudioMultiLingualDataSchema, mulmoStudioMultiLingualFileSchema, speakerDictionarySchema, speakerSchema, mulmoSpeechParamsSchema, mulmoImageParamsSchema, mulmoImageParamsImagesValueSchema, mulmoImageParamsImagesSchema, mulmoFillOptionSchema, mulmoTransitionSchema, mulmoMovieParamsSchema, mulmoSoundEffectParamsSchema, mulmoLipSyncParamsSchema, textSlideParamsSchema, speechOptionsSchema, speakerDataSchema, mulmoCanvasDimensionSchema, mulmoPromptTemplateSchema, mulmoPromptTemplateFileSchema, text2ImageProviderSchema, text2HtmlImageProviderSchema, text2MovieProviderSchema, text2SpeechProviderSchema, mulmoPresentationStyleSchema, multiLingualTextsSchema, mulmoImageAssetSchema, mulmoMermaidMediaSchema, mulmoTextSlideMediaSchema, mulmoMarkdownMediaSchema, mulmoImageMediaSchema, mulmoChartMediaSchema, mediaSourceSchema, mediaSourceMermaidSchema, mulmoSessionStateSchema, mulmoOpenAIImageModelSchema, mulmoGoogleImageModelSchema, mulmoGoogleMovieModelSchema, mulmoReplicateMovieModelSchema, mulmoImagePromptMediaSchema } from "./schema.js";
 import { pdf_modes, pdf_sizes, storyToScriptGenerateMode } from "../utils/const.js";
 import type { LLM } from "../utils/provider2agent.js";
 import { z } from "zod";
@@ -14,6 +14,7 @@ export type MulmoImageParams = z.infer<typeof mulmoImageParamsSchema>;
 export type MulmoImageParamsImagesValue = z.infer<typeof mulmoImageParamsImagesValueSchema>;
 export type MulmoImageParamsImages = z.infer<typeof mulmoImageParamsImagesSchema>;
 export type MulmoFillOption = z.infer<typeof mulmoFillOptionSchema>;
+export type MulmoTransition = z.infer<typeof mulmoTransitionSchema>;
 export type TextSlideParams = z.infer<typeof textSlideParamsSchema>;
 export type Text2ImageProvider = z.infer<typeof text2ImageProviderSchema>;
 export type Text2HtmlImageProvider = z.infer<typeof text2HtmlImageProviderSchema>;

package/lib/utils/context.d.ts

@@ -65,7 +65,7 @@ export declare const createStudioData: (_mulmoScript: MulmoScript, fileName: str
                 style: "aspectFit" | "aspectFill";
             } | undefined;
             transition?: {
-                type: "fade" | "slideout_left";
+                type: "fade" | "slideout_left" | "slideout_right" | "slideout_up" | "slideout_down" | "slidein_left" | "slidein_right" | "slidein_up" | "slidein_down" | "wipeleft" | "wiperight" | "wipeup" | "wipedown" | "wipetl" | "wipetr" | "wipebl" | "wipebr";
                 duration: number;
             } | undefined;
         };
@@ -228,6 +228,10 @@ export declare const createStudioData: (_mulmoScript: MulmoScript, fileName: str
                 fillOption?: {
                     style: "aspectFit" | "aspectFill";
                 } | undefined;
+                transition?: {
+                    type: "fade" | "slideout_left" | "slideout_right" | "slideout_up" | "slideout_down" | "slidein_left" | "slidein_right" | "slidein_up" | "slidein_down" | "wipeleft" | "wiperight" | "wipeup" | "wipedown" | "wipetl" | "wipetr" | "wipebl" | "wipebr";
+                    duration: number;
+                } | undefined;
                 speed?: number | undefined;
             } | undefined;
             soundEffectParams?: {
@@ -383,7 +387,7 @@ export declare const initializeContextFromFiles: (files: FileObject, raiseError:
                     style: "aspectFit" | "aspectFill";
                 } | undefined;
                 transition?: {
-                    type: "fade" | "slideout_left";
+                    type: "fade" | "slideout_left" | "slideout_right" | "slideout_up" | "slideout_down" | "slidein_left" | "slidein_right" | "slidein_up" | "slidein_down" | "wipeleft" | "wiperight" | "wipeup" | "wipedown" | "wipetl" | "wipetr" | "wipebl" | "wipebr";
                     duration: number;
                 } | undefined;
             };
@@ -546,6 +550,10 @@ export declare const initializeContextFromFiles: (files: FileObject, raiseError:
                     fillOption?: {
                         style: "aspectFit" | "aspectFill";
                     } | undefined;
+                    transition?: {
+                        type: "fade" | "slideout_left" | "slideout_right" | "slideout_up" | "slideout_down" | "slidein_left" | "slidein_right" | "slidein_up" | "slidein_down" | "wipeleft" | "wiperight" | "wipeup" | "wipedown" | "wipetl" | "wipetr" | "wipebl" | "wipebr";
+                        duration: number;
+                    } | undefined;
                     speed?: number | undefined;
                 } | undefined;
                 soundEffectParams?: {
@@ -708,7 +716,7 @@ export declare const initializeContextFromFiles: (files: FileObject, raiseError:
                 style: "aspectFit" | "aspectFill";
             } | undefined;
             transition?: {
-                type: "fade" | "slideout_left";
+                type: "fade" | "slideout_left" | "slideout_right" | "slideout_up" | "slideout_down" | "slidein_left" | "slidein_right" | "slidein_up" | "slidein_down" | "wipeleft" | "wiperight" | "wipeup" | "wipedown" | "wipetl" | "wipetr" | "wipebl" | "wipebr";
                 duration: number;
             } | undefined;
         };

package/lib/utils/ffmpeg_utils.js

@@ -46,8 +46,8 @@ export const FfmpegContextGenerateOutput = (context, output, options = []) => {
             .complexFilter(context.filterComplex)
             .outputOptions(options)
             .output(output)
-            .on("start", (__cmdLine) => {
-            GraphAILogger.log("Started FFmpeg ..."); // with command:', cmdLine);
+            .on("start", (cmdLine) => {
+            GraphAILogger.log("Started FFmpeg with command:", cmdLine);
         })
             .on("error", (err, stdout, stderr) => {
             GraphAILogger.error("Error occurred:", err);

package/lib/utils/provider2agent.d.ts

@@ -10,6 +10,7 @@ export declare const provider2TTSAgent: {
         defaultModel: string;
         defaultVoice: string;
         keyName: string;
+        baseURLKeyName: string;
     };
     google: {
         agentName: string;
@@ -49,6 +50,7 @@ export declare const provider2ImageAgent: {
         defaultModel: string;
         models: string[];
         keyName: string;
+        baseURLKeyName: string;
     };
     google: {
         agentName: string;
@@ -138,6 +140,7 @@ export declare const provider2LLMAgent: {
         readonly agentName: "openAIAgent";
         readonly defaultModel: "gpt-5";
         readonly keyName: "OPENAI_API_KEY";
+        readonly baseURLKeyName: "OPENAI_BASE_URL";
         readonly max_tokens: 8192;
         readonly models: readonly ["gpt-5", "gpt-5-nano", "gpt-5-mini", "gpt-4.1", "gpt-4.1-mini", "gpt-4.1-nano", "o3", "o3-mini", "o3-pro", "o1", "o1-pro", "gpt-4o", "gpt-4o-mini"];
     };
@@ -147,6 +150,7 @@ export declare const provider2LLMAgent: {
         readonly max_tokens: 8192;
         readonly models: readonly ["claude-opus-4-1-20250805", "claude-opus-4-20250514", "claude-sonnet-4-20250514", "claude-3-7-sonnet-20250219", "claude-3-haiku-20240307"];
         readonly keyName: "ANTHROPIC_API_KEY";
+        readonly apiKeyNameOverride: "ANTHROPIC_API_TOKEN";
     };
     readonly gemini: {
         readonly agentName: "geminiAgent";

package/lib/utils/provider2agent.js

@@ -11,6 +11,7 @@ export const provider2TTSAgent = {
         defaultModel: "gpt-4o-mini-tts",
         defaultVoice: "shimmer",
         keyName: "OPENAI_API_KEY",
+        baseURLKeyName: "OPENAI_BASE_URL",
     },
     google: {
         agentName: "ttsGoogleAgent",
@@ -52,6 +53,7 @@ export const provider2ImageAgent = {
         defaultModel: "gpt-image-1",
         models: ["dall-e-3", "gpt-image-1"],
         keyName: "OPENAI_API_KEY",
+        baseURLKeyName: "OPENAI_BASE_URL",
     },
     google: {
         agentName: "imageGenAIAgent",
@@ -251,6 +253,7 @@ export const provider2LLMAgent = {
         agentName: "openAIAgent",
         defaultModel: "gpt-5",
         keyName: "OPENAI_API_KEY",
+        baseURLKeyName: "OPENAI_BASE_URL",
         max_tokens: 8192,
         models: [
             "gpt-5",
@@ -274,6 +277,8 @@ export const provider2LLMAgent = {
         max_tokens: 8192,
         models: ["claude-opus-4-1-20250805", "claude-opus-4-20250514", "claude-sonnet-4-20250514", "claude-3-7-sonnet-20250219", "claude-3-haiku-20240307"],
         keyName: "ANTHROPIC_API_KEY",
+        apiKeyNameOverride: "ANTHROPIC_API_TOKEN",
+        // GraphAI is currently using ANTHROPIC_API_KEY, but the official name is ANTHROPIC_API_TOKEN.
     },
     gemini: {
         agentName: "geminiAgent",

package/lib/utils/utils.js

@@ -3,7 +3,7 @@
  * (No Node.js built-ins like fs, path, dotenv, etc.)
  * Works in both Node.js and modern browsers.
  */
-import { provider2LLMAgent } from "./provider2agent.js";
+import { provider2LLMAgent, provider2TTSAgent, provider2ImageAgent, provider2MovieAgent, provider2SoundEffectAgent, provider2LipSyncAgent, } from "./provider2agent.js";
 export const llmPair = (_llm, _model) => {
     const llmKey = _llm ?? "openai";
     const agent = provider2LLMAgent[llmKey]?.agentName ?? provider2LLMAgent.openai.agentName;
@@ -42,61 +42,30 @@ export const settings2GraphAIConfig = (settings, env) => {
     const getKey = (prefix, key) => {
         return settings?.[`${prefix}_${key}`] ?? settings?.[key] ?? env?.[`${prefix}_${key}`] ?? env?.[key];
     };
-    const config = {
-        openAIAgent: {
-            apiKey: getKey("LLM", "OPENAI_API_KEY"),
-            baseURL: getKey("LLM", "OPENAI_BASE_URL"),
-        },
-        anthropicAgent: {
-            apiKey: getKey("LLM", "ANTHROPIC_API_TOKEN"),
-        },
-        imageOpenaiAgent: {
-            apiKey: getKey("IMAGE", "OPENAI_API_KEY"),
-            baseURL: getKey("IMAGE", "OPENAI_BASE_URL"),
-        },
-        imageReplicateAgent: {
-            apiKey: getKey("IMAGE", "REPLICATE_API_TOKEN"),
-        },
-        imageGenAIAgent: {
-            apiKey: getKey("IMAGE", "GEMINI_API_KEY"),
-        },
-        movieReplicateAgent: {
-            apiKey: getKey("MOVIE", "REPLICATE_API_TOKEN"),
-        },
-        movieGenAIAgent: {
-            apiKey: getKey("MOVIE", "GEMINI_API_KEY"),
-        },
-        ttsOpenaiAgent: {
-            apiKey: getKey("TTS", "OPENAI_API_KEY"),
-            baseURL: getKey("TTS", "OPENAI_BASE_URL"),
-        },
-        ttsNijivoiceAgent: {
-            apiKey: getKey("TTS", "NIJIVOICE_API_KEY"),
-        },
-        ttsGoogleAgent: {
-            apiKey: getKey("TTS", "GEMINI_API_KEY"),
-        },
-        ttsGeminiAgent: {
-            apiKey: getKey("TTS", "GEMINI_API_KEY"),
-        },
-        ttsElevenlabsAgent: {
-            apiKey: getKey("TTS", "ELEVENLABS_API_KEY"),
-        },
-        ttsKotodamaAgent: {
-            apiKey: getKey("TTS", "KOTODAMA_API_KEY"),
-        },
-        soundEffectReplicateAgent: {
-            apiKey: getKey("SOUND_EFFECT", "REPLICATE_API_TOKEN"),
-        },
-        lipSyncReplicateAgent: {
-            apiKey: getKey("LIPSYNC", "REPLICATE_API_TOKEN"),
-        },
-        // TODO
-        // browserlessAgent
-        // ttsGoogleAgent
-        // geminiAgent, groqAgent for tool
-        // TAVILY_API_KEY ( for deep research)
+    const addProviderConfigs = (config, providers, prefix) => {
+        Object.entries(providers).forEach(([__provider, info]) => {
+            if (info.agentName === "mediaMockAgent" || !info.keyName)
+                return;
+            const apiKeyName = info.apiKeyNameOverride || info.keyName;
+            config[info.agentName] = {
+                apiKey: getKey(prefix, apiKeyName),
+            };
+            if (info.baseURLKeyName) {
+                config[info.agentName].baseURL = getKey(prefix, info.baseURLKeyName);
+            }
+        });
     };
+    const config = {};
+    addProviderConfigs(config, provider2LLMAgent, "LLM");
+    addProviderConfigs(config, provider2TTSAgent, "TTS");
+    addProviderConfigs(config, provider2ImageAgent, "IMAGE");
+    addProviderConfigs(config, provider2MovieAgent, "MOVIE");
+    addProviderConfigs(config, provider2SoundEffectAgent, "SOUND_EFFECT");
+    addProviderConfigs(config, provider2LipSyncAgent, "LIPSYNC");
+    // TODO
+    // browserlessAgent
+    // geminiAgent, groqAgent for tool
+    // TAVILY_API_KEY ( for deep research)
     return deepClean(config) ?? {};
 };
 export const deepClean = (input) => {

package/lib/utils/video_filter.d.ts

@@ -0,0 +1,7 @@
+import { MulmoVideoFilter } from "../types/index.js";
+/**
+ * Convert video filter objects to FFmpeg filter strings
+ * @param filter - Video filter configuration object
+ * @returns FFmpeg filter string
+ */
+export declare const convertVideoFilterToFFmpeg: (filter: MulmoVideoFilter) => string;

package/lib/utils/video_filter.js

@@ -0,0 +1,149 @@
+// Helper functions for different filter categories
+const convertColorFilter = (filter) => {
+    switch (filter.type) {
+        case "mono":
+            return "hue=s=0";
+        case "sepia":
+            return "colorchannelmixer=.393:.769:.189:0:.349:.686:.168:0:.272:.534:.131";
+        case "brightness_contrast":
+            return `eq=brightness=${filter.brightness}:contrast=${filter.contrast}`;
+        case "hue": {
+            const parts = [`h=${filter.hue ?? 0}`, `s=${filter.saturation ?? 1}`, `b=${filter.brightness ?? 0}`];
+            return `hue=${parts.join(":")}`;
+        }
+        case "colorbalance":
+            return `colorbalance=rs=${filter.rs}:gs=${filter.gs}:bs=${filter.bs}:rm=${filter.rm}:gm=${filter.gm}:bm=${filter.bm}:rh=${filter.rh}:gh=${filter.gh}:bh=${filter.bh}`;
+        case "vibrance":
+            return `vibrance=intensity=${filter.intensity}`;
+        case "negate":
+            return `negate${filter.negate_alpha ? "=negate_alpha=1" : ""}`;
+        case "colorhold":
+            return `colorhold=color=${filter.color}:similarity=${filter.similarity}:blend=${filter.blend}`;
+        case "colorkey":
+            return `colorkey=color=${filter.color}:similarity=${filter.similarity}:blend=${filter.blend}`;
+        default:
+            return null;
+    }
+};
+const convertBlurSharpenFilter = (filter) => {
+    switch (filter.type) {
+        case "blur":
+            return `boxblur=${filter.radius}:${filter.power}`;
+        case "gblur":
+            return `gblur=sigma=${filter.sigma}`;
+        case "avgblur":
+            return `avgblur=sizeX=${filter.sizeX}:sizeY=${filter.sizeY}`;
+        case "unsharp": {
+            const parts = [
+                `luma_msize_x=${filter.luma_msize_x ?? 5}`,
+                `luma_msize_y=${filter.luma_msize_y ?? 5}`,
+                `luma_amount=${filter.luma_amount ?? 1}`,
+                `chroma_msize_x=${filter.chroma_msize_x ?? 5}`,
+                `chroma_msize_y=${filter.chroma_msize_y ?? 5}`,
+                `chroma_amount=${filter.chroma_amount ?? 0}`,
+            ];
+            return `unsharp=${parts.join(":")}`;
+        }
+        default:
+            return null;
+    }
+};
+const convertEdgeNoiseFilter = (filter) => {
+    switch (filter.type) {
+        case "edgedetect": {
+            const parts = [`low=${filter.low ?? 0.2}`, `high=${filter.high ?? 0.4}`, `mode=${filter.mode ?? "wires"}`];
+            return `edgedetect=${parts.join(":")}`;
+        }
+        case "sobel": {
+            const parts = [`planes=${filter.planes ?? 15}`, `scale=${filter.scale ?? 1}`, `delta=${filter.delta ?? 0}`];
+            return `sobel=${parts.join(":")}`;
+        }
+        case "emboss":
+            return "convolution='0 -1 0 -1 5 -1 0 -1 0:0 -1 0 -1 5 -1 0 -1 0:0 -1 0 -1 5 -1 0 -1 0:0 -1 0 -1 5 -1 0 -1 0'";
+        case "glitch":
+            if (filter.style === "blend") {
+                return `tblend=all_mode=difference,noise=alls=${filter.intensity}`;
+            }
+            return `noise=alls=${filter.intensity}:allf=t+u`;
+        case "grain":
+            return `noise=alls=${filter.intensity}:allf=t`;
+        default:
+            return null;
+    }
+};
+const convertTransformEffectFilter = (filter) => {
+    switch (filter.type) {
+        case "hflip":
+            return "hflip";
+        case "vflip":
+            return "vflip";
+        case "rotate":
+            return `rotate=angle=${filter.angle}:fillcolor=${filter.fillcolor}`;
+        case "transpose": {
+            const dirMap = { cclock: "0", clock: "1", cclock_flip: "2", clock_flip: "3" };
+            return `transpose=dir=${dirMap[filter.dir]}`;
+        }
+        case "vignette": {
+            const parts = [`angle=${filter.angle ?? Math.PI / 5}`];
+            if (filter.x0 !== undefined)
+                parts.push(`x0=${filter.x0}`);
+            if (filter.y0 !== undefined)
+                parts.push(`y0=${filter.y0}`);
+            parts.push(`mode=${filter.mode ?? "forward"}`);
+            return `vignette=${parts.join(":")}`;
+        }
+        case "fade":
+            return `fade=type=${filter.mode}:start_frame=${filter.start_frame}:nb_frames=${filter.nb_frames}${filter.alpha ? ":alpha=1" : ""}:color=${filter.color}`;
+        case "pixelize":
+            return `scale=iw/${filter.width}:ih/${filter.height},scale=${filter.width}*iw:${filter.height}*ih:flags=neighbor`;
+        case "pseudocolor":
+            return `pseudocolor=preset=${filter.preset}`;
+        default:
+            return null;
+    }
+};
+const convertTemporalDistortionFilter = (filter) => {
+    switch (filter.type) {
+        case "tmix": {
+            const weights = filter.weights ? `:weights=${filter.weights}` : "";
+            return `tmix=frames=${filter.frames}${weights}`;
+        }
+        case "lagfun": {
+            const parts = [`decay=${filter.decay ?? 0.95}`, `planes=${filter.planes ?? 15}`];
+            return `lagfun=${parts.join(":")}`;
+        }
+        case "threshold":
+            return `threshold=planes=${filter.planes}`;
+        case "elbg":
+            return `elbg=l=${filter.codebook_length}`;
+        case "lensdistortion":
+            return `lenscorrection=k1=${filter.k1}:k2=${filter.k2}`;
+        case "chromashift": {
+            const parts = [`cbh=${filter.cbh ?? 0}`, `cbv=${filter.cbv ?? 0}`, `crh=${filter.crh ?? 0}`, `crv=${filter.crv ?? 0}`, `edge=${filter.edge ?? "smear"}`];
+            return `chromashift=${parts.join(":")}`;
+        }
+        case "deflicker":
+            return `deflicker=size=${filter.size}:mode=${filter.mode}`;
+        case "dctdnoiz":
+            return `dctdnoiz=sigma=${filter.sigma}`;
+        default:
+            return null;
+    }
+};
+/**
+ * Convert video filter objects to FFmpeg filter strings
+ * @param filter - Video filter configuration object
+ * @returns FFmpeg filter string
+ */
+export const convertVideoFilterToFFmpeg = (filter) => {
+    if (filter.type === "custom") {
+        return filter.filter;
+    }
+    // Try each category converter
+    return (convertColorFilter(filter) ||
+        convertBlurSharpenFilter(filter) ||
+        convertEdgeNoiseFilter(filter) ||
+        convertTransformEffectFilter(filter) ||
+        convertTemporalDistortionFilter(filter) ||
+        "");
+};

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "mulmocast",
-  "version": "2.0.8",
+  "version": "2.1.0",
   "description": "",
   "type": "module",
   "main": "lib/index.node.js",
@@ -96,11 +96,11 @@
     "graphai": "^2.0.16",
     "jsdom": "^27.2.0",
     "marked": "^17.0.1",
-    "mulmocast-vision": "^1.0.4",
+    "mulmocast-vision": "^1.0.8",
     "ora": "^9.0.0",
-    "puppeteer": "^24.31.0",
+    "puppeteer": "^24.32.0",
     "replicate": "^1.4.0",
-    "yaml": "^2.8.1",
+    "yaml": "^2.8.2",
     "yargs": "^18.0.0",
     "zod": "^4.1.13"
   },
@@ -114,10 +114,10 @@
     "eslint-config-prettier": "^10.1.8",
     "eslint-plugin-prettier": "^5.5.4",
     "eslint-plugin-sonarjs": "^3.0.5",
-    "prettier": "^3.7.1",
-    "tsx": "^4.20.6",
+    "prettier": "^3.7.4",
+    "tsx": "^4.21.0",
     "typescript": "^5.9.3",
-    "typescript-eslint": "^8.48.0"
+    "typescript-eslint": "^8.48.1"
   },
   "engines": {
     "node": ">=20.0.0"

package/scripts/test/README.md

@@ -12,10 +12,10 @@ This directory contains MulmoScript samples for testing MulmoCast features.
 
 Simple test scripts for basic functionality verification
 
-- **test_hello.json** - 最もシンプルなHello Worldテスト / Simplest Hello World test
-- **test.json** - 基本的な動作テスト / Basic functionality test
-- **test1.json**, **test2.json** - 追加の基本テスト / Additional basic tests
-- **test_beats.json** - Beatの基本機能テスト / Beat basic features test
+- [**test_hello.json**](./test_hello.json) - 最もシンプルなHello Worldテスト / Simplest Hello World test
+- [**test.json**](./test.json) - 基本的な動作テスト / Basic functionality test
+- [**test1.json**](./test1.json), [**test2.json**](./test2.json) - 追加の基本テスト / Additional basic tests
+- [**test_beats.json**](./test_beats.json) - Beatの基本機能テスト / Beat basic features test
 
 ### 🎤 TTS（音声合成）テスト / TTS (Text-to-Speech) Tests
 
@@ -23,13 +23,13 @@ Simple test scripts for basic functionality verification
 
 Tests for various TTS providers
 
-- **test_all_tts.json** - 全TTSプロバイダーのテスト（OpenAI, Gemini, Google, ElevenLabs, Nijivoice） / All TTS providers test
-- **test_audio.json** - 音声パラメータのテスト（padding, duration, movieVolumeなど） / Audio parameters test
-- **test_audio_gemini.json** - Gemini TTSの個別テスト / Gemini TTS specific test
-- **test_audio_instructions.json** - OpenAI TTS instructionsのテスト / OpenAI TTS instructions test
-- **test_elevenlabs_models.json** - ElevenLabsの複数モデルテスト / ElevenLabs multiple models test
-- **test_voices.json** - 複数の音声設定テスト / Multiple voice settings test
-- **test_mixed_providers.json** - 複数のTTSプロバイダー混在テスト / Mixed TTS providers test
+- [**test_all_tts.json**](./test_all_tts.json) - 全TTSプロバイダーのテスト（OpenAI, Gemini, Google, ElevenLabs, Nijivoice） / All TTS providers test
+- [**test_audio.json**](./test_audio.json) - 音声パラメータのテスト（padding, duration, movieVolumeなど） / Audio parameters test
+- [**test_audio_gemini.json**](./test_audio_gemini.json) - Gemini TTSの個別テスト / Gemini TTS specific test
+- [**test_audio_instructions.json**](./test_audio_instructions.json) - OpenAI TTS instructionsのテスト / OpenAI TTS instructions test
+- [**test_elevenlabs_models.json**](./test_elevenlabs_models.json) - ElevenLabsの複数モデルテスト / ElevenLabs multiple models test
+- [**test_voices.json**](./test_voices.json) - 複数の音声設定テスト / Multiple voice settings test
+- [**test_mixed_providers.json**](./test_mixed_providers.json) - 複数のTTSプロバイダー混在テスト / Mixed TTS providers test
 
 ### 🖼️ 画像生成テスト / Image Generation Tests
 
@@ -37,13 +37,13 @@ Tests for various TTS providers
 
 Image generation feature tests
 
-- **test_images.json** - 画像生成の基本テスト / Basic image generation test
-- **test_hello_image.json** - Hello World画像テスト / Hello World image test
-- **test_image_refs.json** - 参照画像を使った生成テスト / Image generation with references
-- **test_markdown.json** - Markdown形式の画像テスト / Markdown format image test
-- **test_html.json** - HTMLから画像生成テスト / HTML to image test
-- **test_vision.json** - Vision APIを使った画像生成テスト / Vision API image test
-- **test_layout.json** - レイアウト機能のテスト / Layout features test
+- [**test_images.json**](./test_images.json) - 画像生成の基本テスト / Basic image generation test
+- [**test_hello_image.json**](./test_hello_image.json) - Hello World画像テスト / Hello World image test
+- [**test_image_refs.json**](./test_image_refs.json) - 参照画像を使った生成テスト / Image generation with references
+- [**test_markdown.json**](./test_markdown.json) - Markdown形式の画像テスト / Markdown format image test
+- [**test_html.json**](./test_html.json) - HTMLから画像生成テスト / HTML to image test
+- [**test_vision.json**](./test_vision.json) - Vision APIを使った画像生成テスト / Vision API image test
+- [**test_layout.json**](./test_layout.json) - レイアウト機能のテスト / Layout features test
 
 ### 🎬 動画生成テスト / Video Generation Tests
 
@@ -51,12 +51,12 @@ Image generation feature tests
 
 Video generation feature tests
 
-- **test_movie.json** - 動画生成の基本テスト（imagePrompt + moviePrompt） / Basic video generation test
-- **test_movie2.json** - 動画生成の追加テスト / Additional video generation test
-- **test_genai_movie.json** - GenAI動画生成テスト / GenAI video generation test
-- **test_genai.json** - GenAI機能テスト / GenAI features test
-- **test_replicate.json** - Replicate動画生成テスト / Replicate video generation test
-- **test_mv.json** - ミュージックビデオ形式のテスト / Music video format test
+- [**test_movie.json**](./test_movie.json) - 動画生成の基本テスト（imagePrompt + moviePrompt） / Basic video generation test
+- [**test_movie2.json**](./test_movie2.json) - 動画生成の追加テスト / Additional video generation test
+- [**test_genai_movie.json**](./test_genai_movie.json) - GenAI動画生成テスト / GenAI video generation test
+- [**test_genai.json**](./test_genai.json) - GenAI機能テスト / GenAI features test
+- [**test_replicate.json**](./test_replicate.json) - Replicate動画生成テスト / Replicate video generation test
+- [**test_mv.json**](./test_mv.json) - ミュージックビデオ形式のテスト / Music video format test
 
 ### 🎭 高度な機能テスト / Advanced Feature Tests
 
@@ -64,17 +64,17 @@ Video generation feature tests
 
 Special features and complex scenario tests
 
-- **test_spillover.json** - 音声スピルオーバー機能テスト / Audio spillover feature test
-- **test_lipsync.json** - リップシンク機能テスト / Lip-sync feature test
-- **test_transition.json** - トランジション効果テスト / Transition effects test
-- **test_transition_no_audio.json** - 音声なしトランジションテスト / Transition without audio test
-- **test_slideout_left_no_audio.json** - スライドアウト効果テスト / Slide-out effect test
-- **test_sound_effect.json** - サウンドエフェクトテスト / Sound effect test
-- **test_voice_over.json** - ボイスオーバー機能テスト / Voice-over feature test
-- **test_captions.json** - 字幕機能テスト / Caption feature test
-- **test_hello_caption.json** - Hello World字幕テスト / Hello World caption test
-- **test_loop.json** - ループ再生テスト / Loop playback test
-- **test_video_speed.json** - 動画速度調整テスト / Video speed adjustment test
+- [**test_spillover.json**](./test_spillover.json) - 音声スピルオーバー機能テスト / Audio spillover feature test
+- [**test_lipsync.json**](./test_lipsync.json) - リップシンク機能テスト / Lip-sync feature test
+- [**test_transition.json**](./test_transition.json) - トランジション効果テスト / Transition effects test
+- [**test_transition_no_audio.json**](./test_transition_no_audio.json) - 音声なしトランジションテスト / Transition without audio test
+- [**test_slideout_left_no_audio.json**](./test_slideout_left_no_audio.json) - スライドアウト効果テスト / Slide-out effect test
+- [**test_sound_effect.json**](./test_sound_effect.json) - サウンドエフェクトテスト / Sound effect test
+- [**test_voice_over.json**](./test_voice_over.json) - ボイスオーバー機能テスト / Voice-over feature test
+- [**test_captions.json**](./test_captions.json) - 字幕機能テスト / Caption feature test
+- [**test_hello_caption.json**](./test_hello_caption.json) - Hello World字幕テスト / Hello World caption test
+- [**test_loop.json**](./test_loop.json) - ループ再生テスト / Loop playback test
+- [**test_video_speed.json**](./test_video_speed.json) - 動画速度調整テスト / Video speed adjustment test
 
 ### 🔧 特殊条件テスト / Special Condition Tests
 
@@ -82,13 +82,13 @@ Special features and complex scenario tests
 
 Edge cases and special condition tests
 
-- **test_no_audio.json** - 音声なし動画テスト / Video without audio test
-- **test_no_audio_with_credit.json** - クレジット付き音声なしテスト / No audio with credits test
-- **test_hello_nobgm.json** - BGMなしテスト / Test without BGM
-- **test_size_error.json** - サイズエラーテスト / Size error test
-- **test_media.json** - メディアファイル処理テスト / Media file processing test
-- **test_order.json** - 順序処理テスト / Order processing test
-- **test_order_portrait.json** - 縦向き順序テスト / Portrait order test
+- [**test_no_audio.json**](./test_no_audio.json) - 音声なし動画テスト / Video without audio test
+- [**test_no_audio_with_credit.json**](./test_no_audio_with_credit.json) - クレジット付き音声なしテスト / No audio with credits test
+- [**test_hello_nobgm.json**](./test_hello_nobgm.json) - BGMなしテスト / Test without BGM
+- [**test_size_error.json**](./test_size_error.json) - サイズエラーテスト / Size error test
+- [**test_media.json**](./test_media.json) - メディアファイル処理テスト / Media file processing test
+- [**test_order.json**](./test_order.json) - 順序処理テスト / Order processing test
+- [**test_order_portrait.json**](./test_order_portrait.json) - 縦向き順序テスト / Portrait order test
 
 ### 🌍 多言語テスト / Multi-language Tests
 
@@ -96,8 +96,8 @@ Edge cases and special condition tests
 
 Language setting tests
 
-- **test_lang.json** - 多言語サポートテスト / Multi-language support test
-- **test_en.json** - 英語専用テスト / English-only test
+- [**test_lang.json**](./test_lang.json) - 多言語サポートテスト / Multi-language support test
+- [**test_en.json**](./test_en.json) - 英語専用テスト / English-only test
 
 ### 🎯 プロバイダー別テスト / Provider-Specific Tests
 
@@ -105,10 +105,10 @@ Language setting tests
 
 Provider-specific feature tests
 
-- **test_hello_google.json** - Google TTS専用テスト / Google TTS specific test
-- **gpt.json** - GPTモデルテスト / GPT model test
-- **mulmo_story.json** - ストーリー形式テスト / Story format test
-- **nano_banana.json** - カスタムサンプル / Custom sample
+- [**test_hello_google.json**](./test_hello_google.json) - Google TTS専用テスト / Google TTS specific test
+- [**gpt.json**](./gpt.json) - GPTモデルテスト / GPT model test
+- [**mulmo_story.json**](./mulmo_story.json) - ストーリー形式テスト / Story format test
+- [**nano_banana.json**](./nano_banana.json) - カスタムサンプル / Custom sample
 
 ## 🚀 使い方 / Usage