mulmocast 2.0.6 → 2.0.8

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (40) hide show
  1. package/lib/actions/audio.js +3 -1
  2. package/lib/agents/image_genai_agent.js +62 -56
  3. package/lib/agents/image_replicate_agent.js +9 -1
  4. package/lib/agents/index.d.ts +2 -1
  5. package/lib/agents/index.js +2 -1
  6. package/lib/agents/movie_genai_agent.d.ts +0 -4
  7. package/lib/agents/movie_genai_agent.js +3 -12
  8. package/lib/agents/test.d.ts +1 -0
  9. package/lib/agents/test.js +12 -0
  10. package/lib/agents/tts_elevenlabs_agent.js +42 -32
  11. package/lib/agents/tts_gemini_agent.js +8 -2
  12. package/lib/agents/tts_kotodama_agent.d.ts +5 -0
  13. package/lib/agents/tts_kotodama_agent.js +76 -0
  14. package/lib/agents/tts_openai_agent.js +1 -1
  15. package/lib/agents/utils.d.ts +1 -0
  16. package/lib/agents/utils.js +1 -0
  17. package/lib/types/agent.d.ts +3 -0
  18. package/lib/types/schema.d.ts +21 -0
  19. package/lib/types/schema.js +3 -2
  20. package/lib/utils/const.d.ts +1 -0
  21. package/lib/utils/const.js +1 -0
  22. package/lib/utils/context.d.ts +8 -0
  23. package/lib/utils/error_cause.d.ts +10 -0
  24. package/lib/utils/error_cause.js +22 -0
  25. package/lib/utils/provider2agent.d.ts +7 -0
  26. package/lib/utils/provider2agent.js +7 -0
  27. package/lib/utils/utils.d.ts +4 -0
  28. package/lib/utils/utils.js +21 -6
  29. package/package.json +4 -4
  30. package/scripts/test/README.md +161 -0
  31. package/scripts/test/test_all_elevenlabs_tts_model.json +111 -0
  32. package/scripts/test/test_all_gemini_tts_model.json +433 -0
  33. package/scripts/test/test_all_image.json +40 -0
  34. package/scripts/test/test_all_image.json~ +45 -0
  35. package/scripts/test/test_all_movie.json +33 -0
  36. package/scripts/test/test_all_movie.json~ +37 -0
  37. package/scripts/test/test_all_tts.json +83 -0
  38. package/scripts/test/test_all_tts.json~ +83 -0
  39. package/scripts/test/test_kotodama.json +57 -0
  40. package/scripts/test/test_kotodama.json~ +0 -0
@@ -19,6 +19,7 @@ export declare const multiLingualTextsSchema: z.ZodRecord<z.ZodString, z.ZodObje
19
19
  export declare const speechOptionsSchema: z.ZodObject<{
20
20
  speed: z.ZodOptional<z.ZodNumber>;
21
21
  instruction: z.ZodOptional<z.ZodString>;
22
+ decoration: z.ZodOptional<z.ZodString>;
22
23
  }, z.core.$strict>;
23
24
  export declare const defaultSpeaker = "Presenter";
24
25
  export declare const text2SpeechProviderSchema: z.ZodDefault<z.ZodEnum<{
@@ -31,6 +32,7 @@ export declare const speakerDataSchema: z.ZodObject<{
31
32
  speechOptions: z.ZodOptional<z.ZodObject<{
32
33
  speed: z.ZodOptional<z.ZodNumber>;
33
34
  instruction: z.ZodOptional<z.ZodString>;
35
+ decoration: z.ZodOptional<z.ZodString>;
34
36
  }, z.core.$strict>>;
35
37
  provider: z.ZodOptional<z.ZodDefault<z.ZodEnum<{
36
38
  [x: string]: string;
@@ -44,6 +46,7 @@ export declare const speakerSchema: z.ZodObject<{
44
46
  speechOptions: z.ZodOptional<z.ZodObject<{
45
47
  speed: z.ZodOptional<z.ZodNumber>;
46
48
  instruction: z.ZodOptional<z.ZodString>;
49
+ decoration: z.ZodOptional<z.ZodString>;
47
50
  }, z.core.$strict>>;
48
51
  provider: z.ZodOptional<z.ZodDefault<z.ZodEnum<{
49
52
  [x: string]: string;
@@ -56,6 +59,7 @@ export declare const speakerSchema: z.ZodObject<{
56
59
  speechOptions: z.ZodOptional<z.ZodObject<{
57
60
  speed: z.ZodOptional<z.ZodNumber>;
58
61
  instruction: z.ZodOptional<z.ZodString>;
62
+ decoration: z.ZodOptional<z.ZodString>;
59
63
  }, z.core.$strict>>;
60
64
  provider: z.ZodOptional<z.ZodDefault<z.ZodEnum<{
61
65
  [x: string]: string;
@@ -70,6 +74,7 @@ export declare const speakerDictionarySchema: z.ZodRecord<z.ZodString, z.ZodObje
70
74
  speechOptions: z.ZodOptional<z.ZodObject<{
71
75
  speed: z.ZodOptional<z.ZodNumber>;
72
76
  instruction: z.ZodOptional<z.ZodString>;
77
+ decoration: z.ZodOptional<z.ZodString>;
73
78
  }, z.core.$strict>>;
74
79
  provider: z.ZodOptional<z.ZodDefault<z.ZodEnum<{
75
80
  [x: string]: string;
@@ -82,6 +87,7 @@ export declare const speakerDictionarySchema: z.ZodRecord<z.ZodString, z.ZodObje
82
87
  speechOptions: z.ZodOptional<z.ZodObject<{
83
88
  speed: z.ZodOptional<z.ZodNumber>;
84
89
  instruction: z.ZodOptional<z.ZodString>;
90
+ decoration: z.ZodOptional<z.ZodString>;
85
91
  }, z.core.$strict>>;
86
92
  provider: z.ZodOptional<z.ZodDefault<z.ZodEnum<{
87
93
  [x: string]: string;
@@ -97,6 +103,7 @@ export declare const mulmoSpeechParamsSchema: z.ZodDefault<z.ZodObject<{
97
103
  speechOptions: z.ZodOptional<z.ZodObject<{
98
104
  speed: z.ZodOptional<z.ZodNumber>;
99
105
  instruction: z.ZodOptional<z.ZodString>;
106
+ decoration: z.ZodOptional<z.ZodString>;
100
107
  }, z.core.$strict>>;
101
108
  provider: z.ZodOptional<z.ZodDefault<z.ZodEnum<{
102
109
  [x: string]: string;
@@ -109,6 +116,7 @@ export declare const mulmoSpeechParamsSchema: z.ZodDefault<z.ZodObject<{
109
116
  speechOptions: z.ZodOptional<z.ZodObject<{
110
117
  speed: z.ZodOptional<z.ZodNumber>;
111
118
  instruction: z.ZodOptional<z.ZodString>;
119
+ decoration: z.ZodOptional<z.ZodString>;
112
120
  }, z.core.$strict>>;
113
121
  provider: z.ZodOptional<z.ZodDefault<z.ZodEnum<{
114
122
  [x: string]: string;
@@ -629,6 +637,7 @@ export declare const mulmoBeatSchema: z.ZodObject<{
629
637
  speechOptions: z.ZodOptional<z.ZodObject<{
630
638
  speed: z.ZodOptional<z.ZodNumber>;
631
639
  instruction: z.ZodOptional<z.ZodString>;
640
+ decoration: z.ZodOptional<z.ZodString>;
632
641
  }, z.core.$strict>>;
633
642
  textSlideParams: z.ZodOptional<z.ZodObject<{
634
643
  cssStyles: z.ZodUnion<readonly [z.ZodString, z.ZodArray<z.ZodString>]>;
@@ -716,6 +725,7 @@ export declare const mulmoPresentationStyleSchema: z.ZodObject<{
716
725
  speechOptions: z.ZodOptional<z.ZodObject<{
717
726
  speed: z.ZodOptional<z.ZodNumber>;
718
727
  instruction: z.ZodOptional<z.ZodString>;
728
+ decoration: z.ZodOptional<z.ZodString>;
719
729
  }, z.core.$strict>>;
720
730
  provider: z.ZodOptional<z.ZodDefault<z.ZodEnum<{
721
731
  [x: string]: string;
@@ -728,6 +738,7 @@ export declare const mulmoPresentationStyleSchema: z.ZodObject<{
728
738
  speechOptions: z.ZodOptional<z.ZodObject<{
729
739
  speed: z.ZodOptional<z.ZodNumber>;
730
740
  instruction: z.ZodOptional<z.ZodString>;
741
+ decoration: z.ZodOptional<z.ZodString>;
731
742
  }, z.core.$strict>>;
732
743
  provider: z.ZodOptional<z.ZodDefault<z.ZodEnum<{
733
744
  [x: string]: string;
@@ -852,6 +863,7 @@ export declare const mulmoScriptSchema: z.ZodObject<{
852
863
  speechOptions: z.ZodOptional<z.ZodObject<{
853
864
  speed: z.ZodOptional<z.ZodNumber>;
854
865
  instruction: z.ZodOptional<z.ZodString>;
866
+ decoration: z.ZodOptional<z.ZodString>;
855
867
  }, z.core.$strict>>;
856
868
  provider: z.ZodOptional<z.ZodDefault<z.ZodEnum<{
857
869
  [x: string]: string;
@@ -864,6 +876,7 @@ export declare const mulmoScriptSchema: z.ZodObject<{
864
876
  speechOptions: z.ZodOptional<z.ZodObject<{
865
877
  speed: z.ZodOptional<z.ZodNumber>;
866
878
  instruction: z.ZodOptional<z.ZodString>;
879
+ decoration: z.ZodOptional<z.ZodString>;
867
880
  }, z.core.$strict>>;
868
881
  provider: z.ZodOptional<z.ZodDefault<z.ZodEnum<{
869
882
  [x: string]: string;
@@ -1133,6 +1146,7 @@ export declare const mulmoScriptSchema: z.ZodObject<{
1133
1146
  speechOptions: z.ZodOptional<z.ZodObject<{
1134
1147
  speed: z.ZodOptional<z.ZodNumber>;
1135
1148
  instruction: z.ZodOptional<z.ZodString>;
1149
+ decoration: z.ZodOptional<z.ZodString>;
1136
1150
  }, z.core.$strict>>;
1137
1151
  textSlideParams: z.ZodOptional<z.ZodObject<{
1138
1152
  cssStyles: z.ZodUnion<readonly [z.ZodString, z.ZodArray<z.ZodString>]>;
@@ -1264,6 +1278,7 @@ export declare const mulmoStudioSchema: z.ZodObject<{
1264
1278
  speechOptions: z.ZodOptional<z.ZodObject<{
1265
1279
  speed: z.ZodOptional<z.ZodNumber>;
1266
1280
  instruction: z.ZodOptional<z.ZodString>;
1281
+ decoration: z.ZodOptional<z.ZodString>;
1267
1282
  }, z.core.$strict>>;
1268
1283
  provider: z.ZodOptional<z.ZodDefault<z.ZodEnum<{
1269
1284
  [x: string]: string;
@@ -1276,6 +1291,7 @@ export declare const mulmoStudioSchema: z.ZodObject<{
1276
1291
  speechOptions: z.ZodOptional<z.ZodObject<{
1277
1292
  speed: z.ZodOptional<z.ZodNumber>;
1278
1293
  instruction: z.ZodOptional<z.ZodString>;
1294
+ decoration: z.ZodOptional<z.ZodString>;
1279
1295
  }, z.core.$strict>>;
1280
1296
  provider: z.ZodOptional<z.ZodDefault<z.ZodEnum<{
1281
1297
  [x: string]: string;
@@ -1545,6 +1561,7 @@ export declare const mulmoStudioSchema: z.ZodObject<{
1545
1561
  speechOptions: z.ZodOptional<z.ZodObject<{
1546
1562
  speed: z.ZodOptional<z.ZodNumber>;
1547
1563
  instruction: z.ZodOptional<z.ZodString>;
1564
+ decoration: z.ZodOptional<z.ZodString>;
1548
1565
  }, z.core.$strict>>;
1549
1566
  textSlideParams: z.ZodOptional<z.ZodObject<{
1550
1567
  cssStyles: z.ZodUnion<readonly [z.ZodString, z.ZodArray<z.ZodString>]>;
@@ -1612,6 +1629,7 @@ export declare const mulmoPromptTemplateSchema: z.ZodObject<{
1612
1629
  speechOptions: z.ZodOptional<z.ZodObject<{
1613
1630
  speed: z.ZodOptional<z.ZodNumber>;
1614
1631
  instruction: z.ZodOptional<z.ZodString>;
1632
+ decoration: z.ZodOptional<z.ZodString>;
1615
1633
  }, z.core.$strict>>;
1616
1634
  provider: z.ZodOptional<z.ZodDefault<z.ZodEnum<{
1617
1635
  [x: string]: string;
@@ -1624,6 +1642,7 @@ export declare const mulmoPromptTemplateSchema: z.ZodObject<{
1624
1642
  speechOptions: z.ZodOptional<z.ZodObject<{
1625
1643
  speed: z.ZodOptional<z.ZodNumber>;
1626
1644
  instruction: z.ZodOptional<z.ZodString>;
1645
+ decoration: z.ZodOptional<z.ZodString>;
1627
1646
  }, z.core.$strict>>;
1628
1647
  provider: z.ZodOptional<z.ZodDefault<z.ZodEnum<{
1629
1648
  [x: string]: string;
@@ -1742,6 +1761,7 @@ export declare const mulmoPromptTemplateFileSchema: z.ZodObject<{
1742
1761
  speechOptions: z.ZodOptional<z.ZodObject<{
1743
1762
  speed: z.ZodOptional<z.ZodNumber>;
1744
1763
  instruction: z.ZodOptional<z.ZodString>;
1764
+ decoration: z.ZodOptional<z.ZodString>;
1745
1765
  }, z.core.$strict>>;
1746
1766
  provider: z.ZodOptional<z.ZodDefault<z.ZodEnum<{
1747
1767
  [x: string]: string;
@@ -1754,6 +1774,7 @@ export declare const mulmoPromptTemplateFileSchema: z.ZodObject<{
1754
1774
  speechOptions: z.ZodOptional<z.ZodObject<{
1755
1775
  speed: z.ZodOptional<z.ZodNumber>;
1756
1776
  instruction: z.ZodOptional<z.ZodString>;
1777
+ decoration: z.ZodOptional<z.ZodString>;
1757
1778
  }, z.core.$strict>>;
1758
1779
  provider: z.ZodOptional<z.ZodDefault<z.ZodEnum<{
1759
1780
  [x: string]: string;
@@ -18,8 +18,9 @@ export const localizedTextSchema = z
18
18
  export const multiLingualTextsSchema = z.record(langSchema, localizedTextSchema);
19
19
  export const speechOptionsSchema = z
20
20
  .object({
21
- speed: z.number().optional(), // default: 1.0
22
- instruction: z.string().optional(),
21
+ speed: z.number().optional(), // default: 1.0 for google and niji voice
22
+ instruction: z.string().optional(), // for tts openai
23
+ decoration: z.string().optional(), // for kotodama. default: neutral
23
24
  })
24
25
  .strict();
25
26
  const speakerIdSchema = z.string();
@@ -11,3 +11,4 @@ export declare const storyToScriptGenerateMode: {
11
11
  oneStep: string;
12
12
  };
13
13
  export declare const bundleTargetLang: string[];
14
+ export declare const ASPECT_RATIOS: string[];
@@ -11,3 +11,4 @@ export const storyToScriptGenerateMode = {
11
11
  oneStep: "one_step",
12
12
  };
13
13
  export const bundleTargetLang = ["ja", "en"];
14
+ export const ASPECT_RATIOS = ["1:1", "9:16", "16:9"];
@@ -17,6 +17,7 @@ export declare const createStudioData: (_mulmoScript: MulmoScript, fileName: str
17
17
  speechOptions?: {
18
18
  speed?: number | undefined;
19
19
  instruction?: string | undefined;
20
+ decoration?: string | undefined;
20
21
  } | undefined;
21
22
  provider?: string | undefined;
22
23
  model?: string | undefined;
@@ -27,6 +28,7 @@ export declare const createStudioData: (_mulmoScript: MulmoScript, fileName: str
27
28
  speechOptions?: {
28
29
  speed?: number | undefined;
29
30
  instruction?: string | undefined;
31
+ decoration?: string | undefined;
30
32
  } | undefined;
31
33
  provider?: string | undefined;
32
34
  model?: string | undefined;
@@ -242,6 +244,7 @@ export declare const createStudioData: (_mulmoScript: MulmoScript, fileName: str
242
244
  speechOptions?: {
243
245
  speed?: number | undefined;
244
246
  instruction?: string | undefined;
247
+ decoration?: string | undefined;
245
248
  } | undefined;
246
249
  textSlideParams?: {
247
250
  cssStyles: string | string[];
@@ -332,6 +335,7 @@ export declare const initializeContextFromFiles: (files: FileObject, raiseError:
332
335
  speechOptions?: {
333
336
  speed?: number | undefined;
334
337
  instruction?: string | undefined;
338
+ decoration?: string | undefined;
335
339
  } | undefined;
336
340
  provider?: string | undefined;
337
341
  model?: string | undefined;
@@ -342,6 +346,7 @@ export declare const initializeContextFromFiles: (files: FileObject, raiseError:
342
346
  speechOptions?: {
343
347
  speed?: number | undefined;
344
348
  instruction?: string | undefined;
349
+ decoration?: string | undefined;
345
350
  } | undefined;
346
351
  provider?: string | undefined;
347
352
  model?: string | undefined;
@@ -557,6 +562,7 @@ export declare const initializeContextFromFiles: (files: FileObject, raiseError:
557
562
  speechOptions?: {
558
563
  speed?: number | undefined;
559
564
  instruction?: string | undefined;
565
+ decoration?: string | undefined;
560
566
  } | undefined;
561
567
  textSlideParams?: {
562
568
  cssStyles: string | string[];
@@ -654,6 +660,7 @@ export declare const initializeContextFromFiles: (files: FileObject, raiseError:
654
660
  speechOptions?: {
655
661
  speed?: number | undefined;
656
662
  instruction?: string | undefined;
663
+ decoration?: string | undefined;
657
664
  } | undefined;
658
665
  provider?: string | undefined;
659
666
  model?: string | undefined;
@@ -664,6 +671,7 @@ export declare const initializeContextFromFiles: (files: FileObject, raiseError:
664
671
  speechOptions?: {
665
672
  speed?: number | undefined;
666
673
  instruction?: string | undefined;
674
+ decoration?: string | undefined;
667
675
  } | undefined;
668
676
  provider?: string | undefined;
669
677
  model?: string | undefined;
@@ -197,3 +197,13 @@ export declare const translateApiKeyMissingError: () => {
197
197
  export declare const hasCause: (err: unknown) => err is Error & {
198
198
  cause: unknown;
199
199
  };
200
+ type Result<T> = {
201
+ ok: true;
202
+ value: T;
203
+ } | {
204
+ ok: false;
205
+ error: Error;
206
+ };
207
+ export declare function resultify<T>(fn: () => Promise<T>): Promise<Result<T>>;
208
+ export declare const getGenAIErrorReason: (error: Error) => any;
209
+ export {};
@@ -226,3 +226,25 @@ export const translateApiKeyMissingError = () => {
226
226
  export const hasCause = (err) => {
227
227
  return err instanceof Error && "cause" in err;
228
228
  };
229
+ export async function resultify(fn) {
230
+ try {
231
+ return { ok: true, value: await fn() };
232
+ }
233
+ catch (error) {
234
+ return { ok: false, error: error };
235
+ }
236
+ }
237
+ export const getGenAIErrorReason = (error) => {
238
+ try {
239
+ if (error instanceof Error && error.message && error.message[0] === "{") {
240
+ const reasonDetail = JSON.parse(error.message).error.details.find((detail) => detail.reason);
241
+ if (reasonDetail) {
242
+ return reasonDetail;
243
+ }
244
+ }
245
+ }
246
+ catch (__error) {
247
+ // nothing.
248
+ }
249
+ return undefined;
250
+ };
@@ -29,6 +29,13 @@ export declare const provider2TTSAgent: {
29
29
  models: string[];
30
30
  keyName: string;
31
31
  };
32
+ kotodama: {
33
+ agentName: string;
34
+ hasLimitedConcurrency: boolean;
35
+ defaultVoice: string;
36
+ defaultDecoration: string;
37
+ keyName: string;
38
+ };
32
39
  mock: {
33
40
  agentName: string;
34
41
  hasLimitedConcurrency: boolean;
@@ -32,6 +32,13 @@ export const provider2TTSAgent = {
32
32
  models: ["eleven_multilingual_v2", "eleven_turbo_v2_5", "eleven_turbo_v2", "eleven_flash_v2_5", "eleven_flash_v2"],
33
33
  keyName: "ELEVENLABS_API_KEY",
34
34
  },
35
+ kotodama: {
36
+ agentName: "ttsKotodamaAgent",
37
+ hasLimitedConcurrency: true,
38
+ defaultVoice: "Atla",
39
+ defaultDecoration: "neutral",
40
+ keyName: "KOTODAMA_API_KEY",
41
+ },
35
42
  mock: {
36
43
  agentName: "mediaMockAgent",
37
44
  hasLimitedConcurrency: true,
@@ -35,4 +35,8 @@ export declare const multiLingualObjectToArray: (multiLingual: MulmoStudioMultiL
35
35
  }>;
36
36
  cacheKey?: string | undefined;
37
37
  }[];
38
+ export declare const getAspectRatio: (canvasSize: {
39
+ width: number;
40
+ height: number;
41
+ }, ASPECT_RATIOS: string[]) => string;
38
42
  export {};
@@ -47,9 +47,8 @@ export const settings2GraphAIConfig = (settings, env) => {
47
47
  apiKey: getKey("LLM", "OPENAI_API_KEY"),
48
48
  baseURL: getKey("LLM", "OPENAI_BASE_URL"),
49
49
  },
50
- ttsOpenaiAgent: {
51
- apiKey: getKey("TTS", "OPENAI_API_KEY"),
52
- baseURL: getKey("TTS", "OPENAI_BASE_URL"),
50
+ anthropicAgent: {
51
+ apiKey: getKey("LLM", "ANTHROPIC_API_TOKEN"),
53
52
  },
54
53
  imageOpenaiAgent: {
55
54
  apiKey: getKey("IMAGE", "OPENAI_API_KEY"),
@@ -61,24 +60,31 @@ export const settings2GraphAIConfig = (settings, env) => {
61
60
  imageGenAIAgent: {
62
61
  apiKey: getKey("IMAGE", "GEMINI_API_KEY"),
63
62
  },
64
- anthropicAgent: {
65
- apiKey: getKey("LLM", "ANTHROPIC_API_TOKEN"),
66
- },
67
63
  movieReplicateAgent: {
68
64
  apiKey: getKey("MOVIE", "REPLICATE_API_TOKEN"),
69
65
  },
70
66
  movieGenAIAgent: {
71
67
  apiKey: getKey("MOVIE", "GEMINI_API_KEY"),
72
68
  },
69
+ ttsOpenaiAgent: {
70
+ apiKey: getKey("TTS", "OPENAI_API_KEY"),
71
+ baseURL: getKey("TTS", "OPENAI_BASE_URL"),
72
+ },
73
73
  ttsNijivoiceAgent: {
74
74
  apiKey: getKey("TTS", "NIJIVOICE_API_KEY"),
75
75
  },
76
+ ttsGoogleAgent: {
77
+ apiKey: getKey("TTS", "GEMINI_API_KEY"),
78
+ },
76
79
  ttsGeminiAgent: {
77
80
  apiKey: getKey("TTS", "GEMINI_API_KEY"),
78
81
  },
79
82
  ttsElevenlabsAgent: {
80
83
  apiKey: getKey("TTS", "ELEVENLABS_API_KEY"),
81
84
  },
85
+ ttsKotodamaAgent: {
86
+ apiKey: getKey("TTS", "KOTODAMA_API_KEY"),
87
+ },
82
88
  soundEffectReplicateAgent: {
83
89
  apiKey: getKey("SOUND_EFFECT", "REPLICATE_API_TOKEN"),
84
90
  },
@@ -126,3 +132,12 @@ export const multiLingualObjectToArray = (multiLingual, beats) => {
126
132
  return { multiLingualTexts: {} };
127
133
  });
128
134
  };
135
+ export const getAspectRatio = (canvasSize, ASPECT_RATIOS) => {
136
+ const target = canvasSize.width / canvasSize.height;
137
+ return ASPECT_RATIOS.reduce((best, ratio) => {
138
+ const [w, h] = ratio.split(":").map(Number);
139
+ const r = w / h;
140
+ const diff = Math.abs(target - r);
141
+ return diff < best.diff ? { ratio, diff } : best;
142
+ }, { ratio: ASPECT_RATIOS[0], diff: Infinity }).ratio;
143
+ };
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "mulmocast",
3
- "version": "2.0.6",
3
+ "version": "2.0.8",
4
4
  "description": "",
5
5
  "type": "module",
6
6
  "main": "lib/index.node.js",
@@ -75,12 +75,12 @@
75
75
  "dependencies": {
76
76
  "@google-cloud/text-to-speech": "^6.4.0",
77
77
  "@google/genai": "^1.30.0",
78
- "@graphai/anthropic_agent": "^2.0.11",
78
+ "@graphai/anthropic_agent": "^2.0.12",
79
79
  "@graphai/browserless_agent": "^2.0.1",
80
80
  "@graphai/gemini_agent": "^2.0.1",
81
81
  "@graphai/groq_agent": "^2.0.2",
82
82
  "@graphai/input_agents": "^1.0.2",
83
- "@graphai/openai_agent": "^2.0.7",
83
+ "@graphai/openai_agent": "^2.0.8",
84
84
  "@graphai/stream_agent_filter": "^2.0.2",
85
85
  "@graphai/vanilla": "^2.0.12",
86
86
  "@graphai/vanilla_node_agents": "^2.0.4",
@@ -114,7 +114,7 @@
114
114
  "eslint-config-prettier": "^10.1.8",
115
115
  "eslint-plugin-prettier": "^5.5.4",
116
116
  "eslint-plugin-sonarjs": "^3.0.5",
117
- "prettier": "^3.6.2",
117
+ "prettier": "^3.7.1",
118
118
  "tsx": "^4.20.6",
119
119
  "typescript": "^5.9.3",
120
120
  "typescript-eslint": "^8.48.0"
@@ -0,0 +1,161 @@
1
+ # MulmoCast Test Scripts
2
+
3
+ このディレクトリには、MulmoCastの機能テスト用のMulmoScriptサンプルが含まれています。
4
+
5
+ This directory contains MulmoScript samples for testing MulmoCast features.
6
+
7
+ ## 📋 テストカテゴリ / Test Categories
8
+
9
+ ### 🎯 基本テスト / Basic Tests
10
+
11
+ **シンプルな動作確認用のテストスクリプト**
12
+
13
+ Simple test scripts for basic functionality verification
14
+
15
+ - **test_hello.json** - 最もシンプルなHello Worldテスト / Simplest Hello World test
16
+ - **test.json** - 基本的な動作テスト / Basic functionality test
17
+ - **test1.json**, **test2.json** - 追加の基本テスト / Additional basic tests
18
+ - **test_beats.json** - Beatの基本機能テスト / Beat basic features test
19
+
20
+ ### 🎤 TTS(音声合成)テスト / TTS (Text-to-Speech) Tests
21
+
22
+ **各種音声合成プロバイダーのテスト**
23
+
24
+ Tests for various TTS providers
25
+
26
+ - **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
27
+ - **test_audio.json** - 音声パラメータのテスト(padding, duration, movieVolumeなど) / Audio parameters test
28
+ - **test_audio_gemini.json** - Gemini TTSの個別テスト / Gemini TTS specific test
29
+ - **test_audio_instructions.json** - OpenAI TTS instructionsのテスト / OpenAI TTS instructions test
30
+ - **test_elevenlabs_models.json** - ElevenLabsの複数モデルテスト / ElevenLabs multiple models test
31
+ - **test_voices.json** - 複数の音声設定テスト / Multiple voice settings test
32
+ - **test_mixed_providers.json** - 複数のTTSプロバイダー混在テスト / Mixed TTS providers test
33
+
34
+ ### 🖼️ 画像生成テスト / Image Generation Tests
35
+
36
+ **画像生成機能のテスト**
37
+
38
+ Image generation feature tests
39
+
40
+ - **test_images.json** - 画像生成の基本テスト / Basic image generation test
41
+ - **test_hello_image.json** - Hello World画像テスト / Hello World image test
42
+ - **test_image_refs.json** - 参照画像を使った生成テスト / Image generation with references
43
+ - **test_markdown.json** - Markdown形式の画像テスト / Markdown format image test
44
+ - **test_html.json** - HTMLから画像生成テスト / HTML to image test
45
+ - **test_vision.json** - Vision APIを使った画像生成テスト / Vision API image test
46
+ - **test_layout.json** - レイアウト機能のテスト / Layout features test
47
+
48
+ ### 🎬 動画生成テスト / Video Generation Tests
49
+
50
+ **動画生成機能のテスト**
51
+
52
+ Video generation feature tests
53
+
54
+ - **test_movie.json** - 動画生成の基本テスト(imagePrompt + moviePrompt) / Basic video generation test
55
+ - **test_movie2.json** - 動画生成の追加テスト / Additional video generation test
56
+ - **test_genai_movie.json** - GenAI動画生成テスト / GenAI video generation test
57
+ - **test_genai.json** - GenAI機能テスト / GenAI features test
58
+ - **test_replicate.json** - Replicate動画生成テスト / Replicate video generation test
59
+ - **test_mv.json** - ミュージックビデオ形式のテスト / Music video format test
60
+
61
+ ### 🎭 高度な機能テスト / Advanced Feature Tests
62
+
63
+ **特殊機能や複雑なシナリオのテスト**
64
+
65
+ Special features and complex scenario tests
66
+
67
+ - **test_spillover.json** - 音声スピルオーバー機能テスト / Audio spillover feature test
68
+ - **test_lipsync.json** - リップシンク機能テスト / Lip-sync feature test
69
+ - **test_transition.json** - トランジション効果テスト / Transition effects test
70
+ - **test_transition_no_audio.json** - 音声なしトランジションテスト / Transition without audio test
71
+ - **test_slideout_left_no_audio.json** - スライドアウト効果テスト / Slide-out effect test
72
+ - **test_sound_effect.json** - サウンドエフェクトテスト / Sound effect test
73
+ - **test_voice_over.json** - ボイスオーバー機能テスト / Voice-over feature test
74
+ - **test_captions.json** - 字幕機能テスト / Caption feature test
75
+ - **test_hello_caption.json** - Hello World字幕テスト / Hello World caption test
76
+ - **test_loop.json** - ループ再生テスト / Loop playback test
77
+ - **test_video_speed.json** - 動画速度調整テスト / Video speed adjustment test
78
+
79
+ ### 🔧 特殊条件テスト / Special Condition Tests
80
+
81
+ **エッジケースや特殊な条件のテスト**
82
+
83
+ Edge cases and special condition tests
84
+
85
+ - **test_no_audio.json** - 音声なし動画テスト / Video without audio test
86
+ - **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
87
+ - **test_hello_nobgm.json** - BGMなしテスト / Test without BGM
88
+ - **test_size_error.json** - サイズエラーテスト / Size error test
89
+ - **test_media.json** - メディアファイル処理テスト / Media file processing test
90
+ - **test_order.json** - 順序処理テスト / Order processing test
91
+ - **test_order_portrait.json** - 縦向き順序テスト / Portrait order test
92
+
93
+ ### 🌍 多言語テスト / Multi-language Tests
94
+
95
+ **言語設定のテスト**
96
+
97
+ Language setting tests
98
+
99
+ - **test_lang.json** - 多言語サポートテスト / Multi-language support test
100
+ - **test_en.json** - 英語専用テスト / English-only test
101
+
102
+ ### 🎯 プロバイダー別テスト / Provider-Specific Tests
103
+
104
+ **特定プロバイダーの機能テスト**
105
+
106
+ Provider-specific feature tests
107
+
108
+ - **test_hello_google.json** - Google TTS専用テスト / Google TTS specific test
109
+ - **gpt.json** - GPTモデルテスト / GPT model test
110
+ - **mulmo_story.json** - ストーリー形式テスト / Story format test
111
+ - **nano_banana.json** - カスタムサンプル / Custom sample
112
+
113
+ ## 🚀 使い方 / Usage
114
+
115
+ ### 基本的な実行方法 / Basic Execution
116
+
117
+ ```bash
118
+ # 動画生成
119
+ # Generate video
120
+ yarn movie scripts/test/test_hello.json
121
+
122
+ # 音声のみ生成
123
+ # Generate audio only
124
+ yarn audio scripts/test/test_audio.json
125
+
126
+ # 画像のみ生成
127
+ # Generate images only
128
+ yarn images scripts/test/test_images.json
129
+ ```
130
+
131
+ ### 強制再生成 / Force Regeneration
132
+
133
+ キャッシュを無視して再生成する場合は `-f` フラグを使用:
134
+
135
+ Use the `-f` flag to ignore cache and regenerate:
136
+
137
+ ```bash
138
+ yarn movie scripts/test/test_hello.json -f
139
+ ```
140
+
141
+ ## 📝 テストスクリプト作成のヒント / Tips for Creating Test Scripts
142
+
143
+ 1. **シンプルから始める** - `test_hello.json` を参考に基本構造を理解
144
+ 2. **機能を段階的に追加** - 一度に複数の機能をテストせず、段階的に追加
145
+ 3. **既存のテストを参考にする** - 同じカテゴリのテストスクリプトを参考に
146
+ 4. **適切な命名** - `test_<feature>.json` の形式で目的が分かりやすい名前を付ける
147
+
148
+ ---
149
+
150
+ 1. **Start simple** - Refer to `test_hello.json` to understand basic structure
151
+ 2. **Add features incrementally** - Don't test multiple features at once
152
+ 3. **Reference existing tests** - Look at tests in the same category
153
+ 4. **Use descriptive naming** - Use `test_<feature>.json` format for clarity
154
+
155
+ ## 🔗 関連ドキュメント / Related Documentation
156
+
157
+ - [メインREADME](../../README.md)
158
+ - [MulmoScript Schema](../../docs/schena.md)
159
+ - [TTS Provider追加手順](../../docs/tts.md)
160
+ - [Image Plugin仕様](../../docs/image_plugin.md)
161
+ - [音声スピルオーバー](../../docs/sound_and_voice.md)