@nodaro/shared 3.20.0 → 3.21.0

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.
package/dist/index.cjs CHANGED
@@ -69,7 +69,7 @@ var MODEL_RECOMMENDATIONS = [
69
69
  { intent: "cheap batch video clips", modelIds: ["veo3.1", "wan-turbo", "bytedance-lite"], note: "VEO 3.1 Fast is the best price/quality balance with native audio." },
70
70
  { intent: "video with start + end frame", modelIds: ["veo3", "veo3.1", "kling-turbo", "minimax", "hailuo-standard", "seedance-2"], note: "All listed support an end frame; VEO uses imageUrls[start, end]." },
71
71
  { intent: "music / song generation", modelIds: ["suno-v6", "suno-v6_wild", "suno-v6_mini", "suno-v5_5"], note: "V6 is the default flagship; V6 Wild for bolder, less predictable results; V6 Mini when speed matters; v5.5 / v5 / v4 keep their own character. Same price." },
72
- { intent: "voice over / narration", modelIds: ["elevenlabs-v3", "elevenlabs-turbo"], note: "v3 supports [audio tags] for emotion; Turbo is cheaper for plain narration." },
72
+ { intent: "voice over / narration", modelIds: ["elevenlabs-v4", "elevenlabs-v3", "elevenlabs-turbo"], note: "v4 is the default: [audio tags] for emotion and up to 10,000 characters per request. v3 is the previous expressive model, still selectable. Turbo is cheaper for plain narration." },
73
73
  { intent: "lip-sync a portrait to audio", modelIds: ["kling-avatar-pro", "kling-avatar", "infinitalk"], note: "Pro for best mouth shape; InfiniTalk for resolution control." },
74
74
  { intent: "transcription / captions", modelIds: ["elevenlabs-stt", "incredibly-fast-whisper", "whisper"], note: "Captions need WORD timestamps: ElevenLabs STT (always) or Incredibly Fast Whisper. Plain Whisper returns phrase segments only." },
75
75
  { intent: "motion transfer (drive a subject by another video)", modelIds: ["motion-transfer", "kling-3.0-motion"], note: "Kling 2.6 base is cheap; Kling 3.0 is premium." }
@@ -2301,7 +2301,6 @@ var AUDIO_MODELS = {
2301
2301
  useCases: ["tts", "voice-over", "narration", "expressive"],
2302
2302
  features: ["audio-tags", "voice-cloning"],
2303
2303
  pricing: [{ identifier: "elevenlabs-v3", credits: 30 }],
2304
- featured: true,
2305
2304
  tts: {
2306
2305
  audioTags: true,
2307
2306
  ssmlBreaks: false,
@@ -2323,6 +2322,8 @@ var AUDIO_MODELS = {
2323
2322
  useCases: ["tts", "voice-over", "narration", "expressive", "long-form"],
2324
2323
  features: ["audio-tags", "voice-cloning"],
2325
2324
  pricing: [{ identifier: "elevenlabs-v4", credits: 30 }],
2325
+ // The default speech model (DEFAULT_TTS_PROVIDER) carries the star.
2326
+ featured: true,
2326
2327
  tts: {
2327
2328
  audioTags: true,
2328
2329
  ssmlBreaks: false,
@@ -3747,6 +3748,7 @@ var TTS_PROVIDERS = [
3747
3748
  "elevenlabs-multilingual",
3748
3749
  "elevenlabs"
3749
3750
  ];
3751
+ var DEFAULT_TTS_PROVIDER = "elevenlabs-v4";
3750
3752
  var TEXT_TO_AUDIO_PROVIDERS = [
3751
3753
  // Replicate disabled
3752
3754
  // "tangoflux",
@@ -21580,6 +21582,7 @@ exports.DEFAULT_TEMPLATE_CATEGORY = DEFAULT_TEMPLATE_CATEGORY;
21580
21582
  exports.DEFAULT_TEXT_TO_AUDIO_PROVIDER = DEFAULT_TEXT_TO_AUDIO_PROVIDER;
21581
21583
  exports.DEFAULT_TRANSCRIBE_NODE_PROVIDER = DEFAULT_TRANSCRIBE_NODE_PROVIDER;
21582
21584
  exports.DEFAULT_TRANSCRIBE_PROVIDER = DEFAULT_TRANSCRIBE_PROVIDER;
21585
+ exports.DEFAULT_TTS_PROVIDER = DEFAULT_TTS_PROVIDER;
21583
21586
  exports.DEFAULT_USAGE_MODE = DEFAULT_USAGE_MODE;
21584
21587
  exports.DEFAULT_VIDEO_ANALYSIS_MODEL = DEFAULT_VIDEO_ANALYSIS_MODEL;
21585
21588
  exports.DEFAULT_VIDEO_ANALYSIS_TIER = DEFAULT_VIDEO_ANALYSIS_TIER;