mulmocast 2.0.7 → 2.0.9

package/lib/actions/audio.js

@@ -2,7 +2,7 @@ import dotenv from "dotenv";
 import { GraphAI, TaskManager, GraphAILogger } from "graphai";
 import * as agents from "@graphai/vanilla";
 import { fileWriteAgent } from "@graphai/vanilla_node_agents";
-import { ttsNijivoiceAgent, ttsOpenaiAgent, ttsGoogleAgent, ttsGeminiAgent, ttsElevenlabsAgent, addBGMAgent, combineAudioFilesAgent, mediaMockAgent, } from "../agents/index.js";
+import { ttsNijivoiceAgent, ttsOpenaiAgent, ttsGoogleAgent, ttsGeminiAgent, ttsElevenlabsAgent, ttsKotodamaAgent, 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";
@@ -108,6 +108,7 @@ const graph_tts = {
                     voice: ":preprocessor.voiceId",
                     speed: ":preprocessor.speechOptions.speed",
                     instructions: ":preprocessor.speechOptions.instruction",
+                    decoration: ":preprocessor.speechOptions.decoration",
                     model: ":preprocessor.model",
                 },
             },
@@ -222,6 +223,7 @@ const audioAgents = {
     ttsNijivoiceAgent,
     ttsGoogleAgent,
     ttsGeminiAgent,
+    ttsKotodamaAgent,
     ttsElevenlabsAgent,
     mediaMockAgent,
     addBGMAgent,

package/lib/agents/index.d.ts

@@ -12,6 +12,7 @@ import ttsNijivoiceAgent from "./tts_nijivoice_agent.js";
 import ttsOpenaiAgent from "./tts_openai_agent.js";
 import ttsGoogleAgent from "./tts_google_agent.js";
 import ttsGeminiAgent from "./tts_gemini_agent.js";
+import ttsKotodamaAgent from "./tts_kotodama_agent.js";
 import validateSchemaAgent from "./validate_schema_agent.js";
 import soundEffectReplicateAgent from "./sound_effect_replicate_agent.js";
 import lipSyncReplicateAgent from "./lipsync_replicate_agent.js";
@@ -20,4 +21,4 @@ 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, imageGenAIAgent, imageOpenaiAgent, imageReplicateAgent, tavilySearchAgent, movieGenAIAgent, movieReplicateAgent, mediaMockAgent, ttsElevenlabsAgent, ttsNijivoiceAgent, ttsOpenaiAgent, ttsGoogleAgent, ttsGeminiAgent, validateSchemaAgent, soundEffectReplicateAgent, lipSyncReplicateAgent, puppeteerCrawlerAgent, };
+export { openAIAgent, fileWriteAgent, browserlessAgent, textInputAgent, addBGMAgent, combineAudioFilesAgent, imageGenAIAgent, imageOpenaiAgent, imageReplicateAgent, tavilySearchAgent, movieGenAIAgent, movieReplicateAgent, mediaMockAgent, ttsElevenlabsAgent, ttsNijivoiceAgent, ttsOpenaiAgent, ttsGoogleAgent, ttsGeminiAgent, ttsKotodamaAgent, validateSchemaAgent, soundEffectReplicateAgent, lipSyncReplicateAgent, puppeteerCrawlerAgent, };

package/lib/agents/index.js

@@ -12,6 +12,7 @@ import ttsNijivoiceAgent from "./tts_nijivoice_agent.js";
 import ttsOpenaiAgent from "./tts_openai_agent.js";
 import ttsGoogleAgent from "./tts_google_agent.js";
 import ttsGeminiAgent from "./tts_gemini_agent.js";
+import ttsKotodamaAgent from "./tts_kotodama_agent.js";
 import validateSchemaAgent from "./validate_schema_agent.js";
 import soundEffectReplicateAgent from "./sound_effect_replicate_agent.js";
 import lipSyncReplicateAgent from "./lipsync_replicate_agent.js";
@@ -21,4 +22,4 @@ 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, imageGenAIAgent, imageOpenaiAgent, imageReplicateAgent, tavilySearchAgent, movieGenAIAgent, movieReplicateAgent, mediaMockAgent, ttsElevenlabsAgent, ttsNijivoiceAgent, ttsOpenaiAgent, ttsGoogleAgent, ttsGeminiAgent, validateSchemaAgent, soundEffectReplicateAgent, lipSyncReplicateAgent, puppeteerCrawlerAgent, };
+export { openAIAgent, fileWriteAgent, browserlessAgent, textInputAgent, addBGMAgent, combineAudioFilesAgent, imageGenAIAgent, imageOpenaiAgent, imageReplicateAgent, tavilySearchAgent, movieGenAIAgent, movieReplicateAgent, mediaMockAgent, ttsElevenlabsAgent, ttsNijivoiceAgent, ttsOpenaiAgent, ttsGoogleAgent, ttsGeminiAgent, ttsKotodamaAgent, validateSchemaAgent, soundEffectReplicateAgent, lipSyncReplicateAgent, puppeteerCrawlerAgent, };

package/lib/types/agent.d.ts

@@ -116,6 +116,9 @@ export type NijivoiceTTSAgentParams = TTSAgentParams & {
     speed: number;
     speed_global: number;
 };
+export type KotodamaTTSAgentParams = TTSAgentParams & {
+    decoration: string;
+};
 export type GoogleTTSAgentParams = TTSAgentParams & {
     speed: number;
 };

package/lib/types/schema.d.ts

@@ -19,6 +19,7 @@ export declare const multiLingualTextsSchema: z.ZodRecord<z.ZodString, z.ZodObje
 export declare const speechOptionsSchema: z.ZodObject<{
     speed: z.ZodOptional<z.ZodNumber>;
     instruction: z.ZodOptional<z.ZodString>;
+    decoration: z.ZodOptional<z.ZodString>;
 }, z.core.$strict>;
 export declare const defaultSpeaker = "Presenter";
 export declare const text2SpeechProviderSchema: z.ZodDefault<z.ZodEnum<{
@@ -31,6 +32,7 @@ export declare const speakerDataSchema: z.ZodObject<{
     speechOptions: z.ZodOptional<z.ZodObject<{
         speed: z.ZodOptional<z.ZodNumber>;
         instruction: z.ZodOptional<z.ZodString>;
+        decoration: z.ZodOptional<z.ZodString>;
     }, z.core.$strict>>;
     provider: z.ZodOptional<z.ZodDefault<z.ZodEnum<{
         [x: string]: string;
@@ -44,6 +46,7 @@ export declare const speakerSchema: z.ZodObject<{
     speechOptions: z.ZodOptional<z.ZodObject<{
         speed: z.ZodOptional<z.ZodNumber>;
         instruction: z.ZodOptional<z.ZodString>;
+        decoration: z.ZodOptional<z.ZodString>;
     }, z.core.$strict>>;
     provider: z.ZodOptional<z.ZodDefault<z.ZodEnum<{
         [x: string]: string;
@@ -56,6 +59,7 @@ export declare const speakerSchema: z.ZodObject<{
         speechOptions: z.ZodOptional<z.ZodObject<{
             speed: z.ZodOptional<z.ZodNumber>;
             instruction: z.ZodOptional<z.ZodString>;
+            decoration: z.ZodOptional<z.ZodString>;
         }, z.core.$strict>>;
         provider: z.ZodOptional<z.ZodDefault<z.ZodEnum<{
             [x: string]: string;
@@ -70,6 +74,7 @@ export declare const speakerDictionarySchema: z.ZodRecord<z.ZodString, z.ZodObje
     speechOptions: z.ZodOptional<z.ZodObject<{
         speed: z.ZodOptional<z.ZodNumber>;
         instruction: z.ZodOptional<z.ZodString>;
+        decoration: z.ZodOptional<z.ZodString>;
     }, z.core.$strict>>;
     provider: z.ZodOptional<z.ZodDefault<z.ZodEnum<{
         [x: string]: string;
@@ -82,6 +87,7 @@ export declare const speakerDictionarySchema: z.ZodRecord<z.ZodString, z.ZodObje
         speechOptions: z.ZodOptional<z.ZodObject<{
             speed: z.ZodOptional<z.ZodNumber>;
             instruction: z.ZodOptional<z.ZodString>;
+            decoration: z.ZodOptional<z.ZodString>;
         }, z.core.$strict>>;
         provider: z.ZodOptional<z.ZodDefault<z.ZodEnum<{
             [x: string]: string;
@@ -97,6 +103,7 @@ export declare const mulmoSpeechParamsSchema: z.ZodDefault<z.ZodObject<{
         speechOptions: z.ZodOptional<z.ZodObject<{
             speed: z.ZodOptional<z.ZodNumber>;
             instruction: z.ZodOptional<z.ZodString>;
+            decoration: z.ZodOptional<z.ZodString>;
         }, z.core.$strict>>;
         provider: z.ZodOptional<z.ZodDefault<z.ZodEnum<{
             [x: string]: string;
@@ -109,6 +116,7 @@ export declare const mulmoSpeechParamsSchema: z.ZodDefault<z.ZodObject<{
             speechOptions: z.ZodOptional<z.ZodObject<{
                 speed: z.ZodOptional<z.ZodNumber>;
                 instruction: z.ZodOptional<z.ZodString>;
+                decoration: z.ZodOptional<z.ZodString>;
             }, z.core.$strict>>;
             provider: z.ZodOptional<z.ZodDefault<z.ZodEnum<{
                 [x: string]: string;
@@ -629,6 +637,7 @@ export declare const mulmoBeatSchema: z.ZodObject<{
     speechOptions: z.ZodOptional<z.ZodObject<{
         speed: z.ZodOptional<z.ZodNumber>;
         instruction: z.ZodOptional<z.ZodString>;
+        decoration: z.ZodOptional<z.ZodString>;
     }, z.core.$strict>>;
     textSlideParams: z.ZodOptional<z.ZodObject<{
         cssStyles: z.ZodUnion<readonly [z.ZodString, z.ZodArray<z.ZodString>]>;
@@ -716,6 +725,7 @@ export declare const mulmoPresentationStyleSchema: z.ZodObject<{
             speechOptions: z.ZodOptional<z.ZodObject<{
                 speed: z.ZodOptional<z.ZodNumber>;
                 instruction: z.ZodOptional<z.ZodString>;
+                decoration: z.ZodOptional<z.ZodString>;
             }, z.core.$strict>>;
             provider: z.ZodOptional<z.ZodDefault<z.ZodEnum<{
                 [x: string]: string;
@@ -728,6 +738,7 @@ export declare const mulmoPresentationStyleSchema: z.ZodObject<{
                 speechOptions: z.ZodOptional<z.ZodObject<{
                     speed: z.ZodOptional<z.ZodNumber>;
                     instruction: z.ZodOptional<z.ZodString>;
+                    decoration: z.ZodOptional<z.ZodString>;
                 }, z.core.$strict>>;
                 provider: z.ZodOptional<z.ZodDefault<z.ZodEnum<{
                     [x: string]: string;
@@ -852,6 +863,7 @@ export declare const mulmoScriptSchema: z.ZodObject<{
             speechOptions: z.ZodOptional<z.ZodObject<{
                 speed: z.ZodOptional<z.ZodNumber>;
                 instruction: z.ZodOptional<z.ZodString>;
+                decoration: z.ZodOptional<z.ZodString>;
             }, z.core.$strict>>;
             provider: z.ZodOptional<z.ZodDefault<z.ZodEnum<{
                 [x: string]: string;
@@ -864,6 +876,7 @@ export declare const mulmoScriptSchema: z.ZodObject<{
                 speechOptions: z.ZodOptional<z.ZodObject<{
                     speed: z.ZodOptional<z.ZodNumber>;
                     instruction: z.ZodOptional<z.ZodString>;
+                    decoration: z.ZodOptional<z.ZodString>;
                 }, z.core.$strict>>;
                 provider: z.ZodOptional<z.ZodDefault<z.ZodEnum<{
                     [x: string]: string;
@@ -1133,6 +1146,7 @@ export declare const mulmoScriptSchema: z.ZodObject<{
         speechOptions: z.ZodOptional<z.ZodObject<{
             speed: z.ZodOptional<z.ZodNumber>;
             instruction: z.ZodOptional<z.ZodString>;
+            decoration: z.ZodOptional<z.ZodString>;
         }, z.core.$strict>>;
         textSlideParams: z.ZodOptional<z.ZodObject<{
             cssStyles: z.ZodUnion<readonly [z.ZodString, z.ZodArray<z.ZodString>]>;
@@ -1264,6 +1278,7 @@ export declare const mulmoStudioSchema: z.ZodObject<{
                 speechOptions: z.ZodOptional<z.ZodObject<{
                     speed: z.ZodOptional<z.ZodNumber>;
                     instruction: z.ZodOptional<z.ZodString>;
+                    decoration: z.ZodOptional<z.ZodString>;
                 }, z.core.$strict>>;
                 provider: z.ZodOptional<z.ZodDefault<z.ZodEnum<{
                     [x: string]: string;
@@ -1276,6 +1291,7 @@ export declare const mulmoStudioSchema: z.ZodObject<{
                     speechOptions: z.ZodOptional<z.ZodObject<{
                         speed: z.ZodOptional<z.ZodNumber>;
                         instruction: z.ZodOptional<z.ZodString>;
+                        decoration: z.ZodOptional<z.ZodString>;
                     }, z.core.$strict>>;
                     provider: z.ZodOptional<z.ZodDefault<z.ZodEnum<{
                         [x: string]: string;
@@ -1545,6 +1561,7 @@ export declare const mulmoStudioSchema: z.ZodObject<{
             speechOptions: z.ZodOptional<z.ZodObject<{
                 speed: z.ZodOptional<z.ZodNumber>;
                 instruction: z.ZodOptional<z.ZodString>;
+                decoration: z.ZodOptional<z.ZodString>;
             }, z.core.$strict>>;
             textSlideParams: z.ZodOptional<z.ZodObject<{
                 cssStyles: z.ZodUnion<readonly [z.ZodString, z.ZodArray<z.ZodString>]>;
@@ -1612,6 +1629,7 @@ export declare const mulmoPromptTemplateSchema: z.ZodObject<{
                 speechOptions: z.ZodOptional<z.ZodObject<{
                     speed: z.ZodOptional<z.ZodNumber>;
                     instruction: z.ZodOptional<z.ZodString>;
+                    decoration: z.ZodOptional<z.ZodString>;
                 }, z.core.$strict>>;
                 provider: z.ZodOptional<z.ZodDefault<z.ZodEnum<{
                     [x: string]: string;
@@ -1624,6 +1642,7 @@ export declare const mulmoPromptTemplateSchema: z.ZodObject<{
                     speechOptions: z.ZodOptional<z.ZodObject<{
                         speed: z.ZodOptional<z.ZodNumber>;
                         instruction: z.ZodOptional<z.ZodString>;
+                        decoration: z.ZodOptional<z.ZodString>;
                     }, z.core.$strict>>;
                     provider: z.ZodOptional<z.ZodDefault<z.ZodEnum<{
                         [x: string]: string;
@@ -1742,6 +1761,7 @@ export declare const mulmoPromptTemplateFileSchema: z.ZodObject<{
                 speechOptions: z.ZodOptional<z.ZodObject<{
                     speed: z.ZodOptional<z.ZodNumber>;
                     instruction: z.ZodOptional<z.ZodString>;
+                    decoration: z.ZodOptional<z.ZodString>;
                 }, z.core.$strict>>;
                 provider: z.ZodOptional<z.ZodDefault<z.ZodEnum<{
                     [x: string]: string;
@@ -1754,6 +1774,7 @@ export declare const mulmoPromptTemplateFileSchema: z.ZodObject<{
                     speechOptions: z.ZodOptional<z.ZodObject<{
                         speed: z.ZodOptional<z.ZodNumber>;
                         instruction: z.ZodOptional<z.ZodString>;
+                        decoration: z.ZodOptional<z.ZodString>;
                     }, z.core.$strict>>;
                     provider: z.ZodOptional<z.ZodDefault<z.ZodEnum<{
                         [x: string]: string;

package/lib/types/schema.js

@@ -18,8 +18,9 @@ export const localizedTextSchema = z
 export const multiLingualTextsSchema = z.record(langSchema, localizedTextSchema);
 export const speechOptionsSchema = z
     .object({
-    speed: z.number().optional(), // default: 1.0
-    instruction: z.string().optional(),
+    speed: z.number().optional(), // default: 1.0 for google and niji voice
+    instruction: z.string().optional(), // for tts openai
+    decoration: z.string().optional(), // for kotodama. default: neutral
 })
     .strict();
 const speakerIdSchema = z.string();

package/lib/utils/context.d.ts

@@ -17,6 +17,7 @@ export declare const createStudioData: (_mulmoScript: MulmoScript, fileName: str
                 speechOptions?: {
                     speed?: number | undefined;
                     instruction?: string | undefined;
+                    decoration?: string | undefined;
                 } | undefined;
                 provider?: string | undefined;
                 model?: string | undefined;
@@ -27,6 +28,7 @@ export declare const createStudioData: (_mulmoScript: MulmoScript, fileName: str
                     speechOptions?: {
                         speed?: number | undefined;
                         instruction?: string | undefined;
+                        decoration?: string | undefined;
                     } | undefined;
                     provider?: string | undefined;
                     model?: string | undefined;
@@ -242,6 +244,7 @@ export declare const createStudioData: (_mulmoScript: MulmoScript, fileName: str
             speechOptions?: {
                 speed?: number | undefined;
                 instruction?: string | undefined;
+                decoration?: string | undefined;
             } | undefined;
             textSlideParams?: {
                 cssStyles: string | string[];
@@ -332,6 +335,7 @@ export declare const initializeContextFromFiles: (files: FileObject, raiseError:
                     speechOptions?: {
                         speed?: number | undefined;
                         instruction?: string | undefined;
+                        decoration?: string | undefined;
                     } | undefined;
                     provider?: string | undefined;
                     model?: string | undefined;
@@ -342,6 +346,7 @@ export declare const initializeContextFromFiles: (files: FileObject, raiseError:
                         speechOptions?: {
                             speed?: number | undefined;
                             instruction?: string | undefined;
+                            decoration?: string | undefined;
                         } | undefined;
                         provider?: string | undefined;
                         model?: string | undefined;
@@ -557,6 +562,7 @@ export declare const initializeContextFromFiles: (files: FileObject, raiseError:
                 speechOptions?: {
                     speed?: number | undefined;
                     instruction?: string | undefined;
+                    decoration?: string | undefined;
                 } | undefined;
                 textSlideParams?: {
                     cssStyles: string | string[];
@@ -654,6 +660,7 @@ export declare const initializeContextFromFiles: (files: FileObject, raiseError:
                 speechOptions?: {
                     speed?: number | undefined;
                     instruction?: string | undefined;
+                    decoration?: string | undefined;
                 } | undefined;
                 provider?: string | undefined;
                 model?: string | undefined;
@@ -664,6 +671,7 @@ export declare const initializeContextFromFiles: (files: FileObject, raiseError:
                     speechOptions?: {
                         speed?: number | undefined;
                         instruction?: string | undefined;
+                        decoration?: string | undefined;
                     } | undefined;
                     provider?: string | undefined;
                     model?: string | undefined;

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;
@@ -29,6 +30,13 @@ export declare const provider2TTSAgent: {
         models: string[];
         keyName: string;
     };
+    kotodama: {
+        agentName: string;
+        hasLimitedConcurrency: boolean;
+        defaultVoice: string;
+        defaultDecoration: string;
+        keyName: string;
+    };
     mock: {
         agentName: string;
         hasLimitedConcurrency: boolean;
@@ -42,6 +50,7 @@ export declare const provider2ImageAgent: {
         defaultModel: string;
         models: string[];
         keyName: string;
+        baseURLKeyName: string;
     };
     google: {
         agentName: string;
@@ -131,6 +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"];
     };
@@ -140,6 +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",
@@ -32,6 +33,13 @@ export const provider2TTSAgent = {
         models: ["eleven_multilingual_v2", "eleven_turbo_v2_5", "eleven_turbo_v2", "eleven_flash_v2_5", "eleven_flash_v2"],
         keyName: "ELEVENLABS_API_KEY",
     },
+    kotodama: {
+        agentName: "ttsKotodamaAgent",
+        hasLimitedConcurrency: true,
+        defaultVoice: "Atla",
+        defaultDecoration: "neutral",
+        keyName: "KOTODAMA_API_KEY",
+    },
     mock: {
         agentName: "mediaMockAgent",
         hasLimitedConcurrency: true,
@@ -45,6 +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",
@@ -244,6 +253,7 @@ export const provider2LLMAgent = {
         agentName: "openAIAgent",
         defaultModel: "gpt-5",
         keyName: "OPENAI_API_KEY",
+        baseURLKeyName: "OPENAI_BASE_URL",
         max_tokens: 8192,
         models: [
             "gpt-5",
@@ -267,6 +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;
@@ -42,58 +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"),
-        },
-        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/package.json

@@ -1,6 +1,6 @@
 {
   "name": "mulmocast",
-  "version": "2.0.7",
+  "version": "2.0.9",
   "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
 

package/scripts/test/test_kotodama.json

@@ -0,0 +1,57 @@
+{
+  "$mulmocast": {
+    "version": "1.1"
+  },
+  "lang": "en",
+  "title": "Media Test",
+  "speechParams": {
+    "speakers": {
+      "Presenter": {
+        "provider": "kotodama",
+        "voiceId": "Poporo"
+      },
+      "Shion": {
+        "provider": "kotodama",
+        "speechOptions": {
+          "decoration": "laughing"
+        },
+        "voiceId": "Shion"
+      }
+    }
+  },
+  "beats": [
+    {
+      "speaker": "Presenter",
+      "text": "こんにちは",
+      "image": {
+        "type": "textSlide",
+        "slide": {
+          "title": "Hello, kotodama"
+        }
+      }
+    },
+    {
+      "speaker": "Shion",
+      "text": "こんにちは",
+      "image": {
+        "type": "textSlide",
+        "slide": {
+          "title": "Hello, kotodama"
+        }
+      }
+    },
+    {
+      "speaker": "Presenter",
+      "text": "ハッピーだね",
+      "speechOptions": {
+        "decoration": "happy"
+      },
+      "image": {
+        "type": "textSlide",
+        "slide": {
+          "title": "Hello, kotodama"
+        }
+      }
+    }
+  ]
+}

package/scripts/test/test_all_image.json~

@@ -1,45 +0,0 @@
-{
-  "$mulmocast": {
-    "version": "1.1"
-  },
-  "lang": "ja",
-  "title": "All Image Providers Test",
-  "imageParams": {
-    "canvasSize": {
-      "width": 1024,
-      "height": 1024
-    }
-  },
-  "beats": [
-    {
-      "speaker": "Presenter",
-      "text": "こんにちは、テストです。",
-      "image": {
-        "type": "generated",
-        "prompt": "美しい日本庭園",
-        "provider": "openai",
-        "model": "gpt-image-1"
-      }
-    },
-    {
-      "speaker": "Presenter",
-      "text": "こんにちは、テストです。",
-      "image": {
-        "type": "generated",
-        "prompt": "美しい日本庭園",
-        "provider": "google",
-        "model": "gemini-2.5-flash-image"
-      }
-    },
-    {
-      "speaker": "Presenter",
-      "text": "こんにちは、テストです。",
-      "image": {
-        "type": "generated",
-        "prompt": "美しい日本庭園",
-        "provider": "replicate",
-        "model": "bytedance/seedream-4"
-      }
-    }
-  ]
-}

package/scripts/test/test_all_movie.json~

@@ -1,37 +0,0 @@
-{
-  "$mulmocast": {
-    "version": "1.1"
-  },
-  "lang": "ja",
-  "title": "All Movie Providers Test",
-  "imageParams": {
-    "canvasSize": {
-      "width": 1280,
-      "height": 720
-    }
-  },
-  "beats": [
-    {
-      "speaker": "Presenter",
-      "text": "こんにちは、テストです。",
-      "image": {
-        "type": "movie",
-        "prompt": "美しい日本庭園を散歩するカメラワーク",
-        "provider": "google",
-        "model": "veo-2.0-generate-001",
-        "duration": 5
-      }
-    },
-    {
-      "speaker": "Presenter",
-      "text": "こんにちは、テストです。",
-      "image": {
-        "type": "movie",
-        "prompt": "美しい日本庭園を散歩するカメラワーク",
-        "provider": "replicate",
-        "model": "bytedance/seedance-1-lite",
-        "duration": 5
-      }
-    }
-  ]
-}

package/scripts/test/test_all_tts.json~

@@ -1,83 +0,0 @@
-{
-  "$mulmocast": {
-    "version": "1.1"
-  },
-  "lang": "ja",
-  "title": "All TTS Providers Test",
-  "speechParams": {
-    "speakers": {
-      "OpenAI": {
-        "provider": "openai",
-        "voiceId": "shimmer"
-      },
-      "Gemini": {
-        "provider": "gemini",
-        "voiceId": "Kore"
-      },
-      "Google": {
-        "provider": "google",
-        "voiceId": "ja-JP-Standard-A"
-      },
-      "ElevenLabs": {
-        "provider": "elevenlabs",
-        "voiceId": "3JDquces8E8bkmvbh6Bc"
-      },
-      "Nijivoice": {
-        "provider": "nijivoice",
-        "voiceId": "231e0170-0ece-4155-be44-231423062f41"
-      }
-    }
-  },
-  "beats": [
-    {
-      "speaker": "OpenAI",
-      "text": "こんにちは、テストです。",
-      "image": {
-        "type": "textSlide",
-        "slide": {
-          "title": "OpenAI TTS"
-        }
-      }
-    },
-    {
-      "speaker": "Gemini",
-      "text": "こんにちは、テストです。",
-      "image": {
-        "type": "textSlide",
-        "slide": {
-          "title": "Gemini TTS"
-        }
-      }
-    },
-    {
-      "speaker": "Google",
-      "text": "こんにちは、テストです。",
-      "image": {
-        "type": "textSlide",
-        "slide": {
-          "title": "Google TTS"
-        }
-      }
-    },
-    {
-      "speaker": "ElevenLabs",
-      "text": "こんにちは、テストです。",
-      "image": {
-        "type": "textSlide",
-        "slide": {
-          "title": "ElevenLabs TTS"
-        }
-      }
-    },
-    {
-      "speaker": "Nijivoice",
-      "text": "こんにちは、テストです。",
-      "image": {
-        "type": "textSlide",
-        "slide": {
-          "title": "Nijivoice TTS"
-        }
-      }
-    }
-  ]
-}

package/scripts/test/test_audio_gemini.json~

@@ -1,67 +0,0 @@
-{
-  "$mulmocast": {
-    "version": "1.1"
-  },
-  "lang": "en",
-  "title": "Audio Instructions Test",
-  "speechParams": {
-    "speakers": {
-      "Presenter": {
-        "provider": "google",
-        "voiceId": "ja-JP-Standard-A"
-      },
-      "Presenter2": {
-        "provider": "google",
-        "voiceId": "ja-JP-Standard-B"
-      }
-    }
-  },
-  "beats": [
-    {
-      "speaker": "Presenter",
-      "text": "Hello, I'm a presenter. I have no instructions.",
-      "image": {
-        "type": "textSlide",
-        "slide": {
-          "title": "Presenter"
-        }
-      }
-    },
-    {
-      "speaker": "Presenter2",
-      "text": "Hello, I'm a presenter 2. My instructions are 'Speak in a cheerful and positive tone'.",
-      "image": {
-        "type": "textSlide",
-        "slide": {
-          "title": "Presenter 2"
-        }
-      }
-    },
-    {
-      "speaker": "Presenter",
-      "text": "Hello, I'm a presenter. I have a British English instruction.",
-      "speechOptions": {
-        "instruction": "Speak in British English."
-      },
-      "image": {
-        "type": "textSlide",
-        "slide": {
-          "title": "Presenter with British English instruction"
-        }
-      }
-    },
-    {
-      "speaker": "Presenter",
-      "text": "Hello, I'm a presenter. I have a whisper instruction.",
-      "speechOptions": {
-        "instruction": "Whisper softly, like a pillow talk."
-      },
-      "image": {
-        "type": "textSlide",
-        "slide": {
-          "title": "Presenter with whisper instruction"
-        }
-      }
-    }
-  ]
-}

package/scripts/test/test_genai2.json~

@@ -1,84 +0,0 @@
-{
-  "$mulmocast": { "version": "1.1" },
-  "imageParams": {
-    "provider": "google",
-    "style": "<style>Photo realistic.</style>"
-  },
-  "movieParams": {
-    "provider": "google"
-  },
-  "lang": "en",
-  "beats": [
-    {
-      "id": "gemini_3_pro_image_preview",
-      "text": "image generated by gemini-3-pro-image-preview",
-      "imagePrompt": "a woman is walking through a busy Tokyo street at night, she is wearing dark sunglasses",
-      "imageParams": {
-        "model": "gemini-3-pro-image-preview"
-      }
-    },
-    {
-      "id": "gemini_2_5_flash_image",
-      "text": "image generated by gemini-2.5-flash-image",
-      "imagePrompt": "a woman is walking through a busy Tokyo street at night, she is wearing dark sunglasses",
-      "imageParams": {
-        "model": "gemini-2.5-flash-image"
-      }
-    },
-    {
-      "id": "imagen_4",
-      "text": "image generated by imagen-4",
-      "imagePrompt": "a woman is walking through a busy Tokyo street at night, she is wearing dark sunglasses"
-    },
-    {
-      "id": "imagen_4_ultra",
-      "text": "image generated by imagen-4",
-      "imagePrompt": "a woman is walking through a busy Tokyo street at night, she is wearing dark sunglasses",
-      "imageParams": {
-        "model": "imagen-4.0-ultra-generate-preview-06-06"
-      }
-    },
-    {
-      "id": "genai_veo2",
-      "text": "movie generated by veo2",
-      "duration": 5,
-      "moviePrompt": "a woman is walking through a busy Tokyo street at night, she is wearing dark sunglasses"
-    },
-    {
-      "id": "genai_veo2_image",
-      "text": "movie generated by veo2 with image",
-      "duration": 5,
-      "imagePrompt": "a woman is walking through a busy Tokyo street at night, she is wearing dark sunglasses",
-      "moviePrompt": "a woman takes a selfie with her phone"
-    },
-    {
-      "id": "genai_veo3",
-      "text": "movie generated by veo3",
-      "moviePrompt": "a woman is walking through a busy Tokyo street at night, she is wearing dark sunglasses",
-      "movieParams": {
-        "model": "veo-3.0-generate-001"
-      }
-    },
-    {
-      "id": "genai_veo3_1",
-      "text": "movie generated by veo3_1",
-      "moviePrompt": "a woman is walking through a busy Tokyo street at night, she is wearing dark sunglasses",
-      "movieParams": {
-        "model": "veo-3.1-generate-preview"
-      }
-    },
-    {
-      "id": "genai_veo3_image",
-      "text": "movie generated by veo3",
-      "duration": 5,
-      "imagePrompt": "a woman is walking through a busy Tokyo street at night, she is wearing dark sunglasses",
-      "imageParams": {
-        "model": "gemini-2.5-flash-image"
-      },
-      "moviePrompt": "a woman is walking through a busy Tokyo street at night, she is wearing dark sunglasses",
-      "movieParams": {
-        "model": "veo-3.0-generate-001"
-      }
-    }
-  ]
-}

package/scripts/test/test_genai_movie.json~

@@ -1,22 +0,0 @@
-{
-  "$mulmocast": { "version": "1.1" },
-  "imageParams": {
-    "provider": "google",
-    "style": "<style>Photo realistic.</style>"
-  },
-  "canvasSize": {
-    "width": 720,
-    "height": 1280
-  },
-  "lang": "en",
-  "movieParams": {
-    "provider": "google",
-    "model": "veo-3.1-generate-preview"
-  },
-  "beats": [
-    {
-      "moviePrompt": "A butterfly flying in slow motion",
-      "duration": 20
-    }
-  ]
-}

package/scripts/test/test_lipsync2.json~

@@ -1,24 +0,0 @@
-{
-  "$mulmocast": {
-    "version": "1.1"
-  },
-  "lang": "en",
-  "movieParams": {
-    "provider": "google"
-  },
-  "lipSyncParams": {
-    "provider": "replicate",
-    "model": "bytedance/latentsync"
-  },
-  "canvasSize": {
-    "width": 1280,
-    "height": 720
-  },
-  "beats": [
-    {
-      "text": "Hello, I'm macoro. Hello, I'm macoro. Hello, I'm macoro.",
-      "moviePrompt": "macoro is speaking",
-      "enableLipSync": true
-    }
-  ]
-}

package/scripts/test/test_movie2.json~

@@ -1,40 +0,0 @@
-{
-  "$mulmocast": {
-    "version": "1.1"
-  },
-  "lang": "en",
-  "movieParams": {
-    "provider": "google"
-  },
-  "canvasSize": {
-    "width": 720,
-    "height": 1280
-  },
-  "imageParams": {
-    "provider": "openai",
-    "model": "dall-e-3",
-    "style": "Photo realistic, cinematic style.",
-    "images": {
-      "optimus": {
-        "type": "image",
-        "source": {
-          "kind": "url",
-          "url": "https://raw.githubusercontent.com/receptron/mulmocast-media/refs/heads/main/characters/optimus.png"
-        }
-      }
-    }
-  },
-  "beats": [
-    {
-      "text": "Image with both image and movie prompt",
-      "imagePrompt": "巨大なロケット「Starship」が発射台から打ち上がろうとしている様子。空には星と火星が浮かんでいる。",
-      "moviePrompt": "Startship lifts off.",
-      "duration": 5
-    },
-    {
-      "text": "Image with only movie prompt",
-      "moviePrompt": "Startship lifts off.",
-      "duration": 5
-    }
-  ]
-}

package/scripts/test/test_play_to_end.json~

@@ -1,65 +0,0 @@
-{
-  "$mulmocast": {
-    "version": "1.1",
-    "credit": "closing"
-  },
-  "canvasSize": {
-    "width": 1536,
-    "height": 1024
-  },
-  "speechParams": {
-    "speakers": {
-      "Presenter": {
-        "displayName": {
-          "en": "Presenter"
-        },
-        "voiceId": "shimmer"
-      }
-    }
-  },
-  "imageParams": {
-    "provider": "openai",
-    "style": "<style>Vibrant 3D animation style inspired by K-pop aesthetics, with glossy, stylized characters. The overall visual style combines elements of modern animation, game cinematics, and fashion-forward character design, with sleek outlines, glowing effects, and a polished, cinematic finish.</style>",
-    "images": {
-      "min": {
-        "type": "image",
-        "source": {
-          "kind": "url",
-          "url": "https://raw.githubusercontent.com/receptron/mulmocast-media/refs/heads/main/characters/min_anime.png"
-        }
-      }
-    }
-  },
-  "movieParams": {
-    "provider": "replicate"
-  },
-  "soundEffectParams": {
-    "provider": "replicate"
-  },
-  "captionParams": {
-    "lang": "en",
-    "styles": ["font-size: 64px", "width: 90%", "padding-left: 5%", "padding-right: 5%"]
-  },
-  "audioParams": {
-    "padding": 0,
-    "introPadding": 0,
-    "closingPadding": 0,
-    "outroPadding": 0,
-    "bgm": {
-      "kind": "url",
-      "url": "https://raw.githubusercontent.com/receptron/mulmocast-media/refs/heads/main/music/finetuning_with_you.mp3"
-    },
-    "bgmVolume": 1,
-    "audioVolume": 0,
-    "suppressSpeech": true
-  },
-  "title": "Music Video",
-  "lang": "en",
-  "beats": [
-    {
-      "text": "Finetuning with you",
-      "moviePrompt": "The singer preparing to sing a song.",
-      "playGenMovieToEnd": true
-    }
-  ]
-}