Files
diodiogod-TTS-Audio-Suite/example_workflows/Higgs Audio v3 Integration.json

1213 lines
25 KiB
JSON

{
"id": "4a7cdb14-f535-4923-861b-59ba2c7ee043",
"revision": 0,
"last_node_id": 157,
"last_link_id": 265,
"nodes": [
{
"id": 47,
"type": "UnifiedTTSTextNode",
"pos": [
-1150,
1110
],
"size": [
400,
379.5921325683594
],
"flags": {},
"order": 19,
"mode": 0,
"inputs": [
{
"name": "TTS_engine",
"type": "TTS_ENGINE",
"link": 252
},
{
"name": "opt_narrator",
"shape": 7,
"type": "*",
"link": 257
},
{
"name": "text",
"type": "STRING",
"widget": {
"name": "text"
},
"link": 182
}
],
"outputs": [
{
"name": "audio",
"type": "AUDIO",
"links": [
246
]
},
{
"name": "generation_info",
"type": "STRING",
"links": [
100
]
}
],
"properties": {
"cnr_id": "tts_audio_suite",
"ver": "ee95cad1f155eceb1442723c7f351949b30361e3",
"Node name for S&R": "UnifiedTTSTextNode",
"ue_properties": {
"widget_ue_connectable": {
"text": true
},
"version": "7.4.1",
"input_ue_unconnectable": {}
}
},
"widgets_values": [
"Hello! This is unified TTS with character switching support.\n[Alice] Hi there! I'm Alice speaking with the selected TTS engine.\n[Bob] And I'm Bob! This works with any TTS engine.\nBack to the main narrator voice for the conclusion.",
"none",
1552347959,
"fixed",
true,
400,
"crossfade",
100,
true,
0
],
"color": "#223",
"bgcolor": "#335"
},
{
"id": 50,
"type": "PreviewAny",
"pos": [
-640,
1270
],
"size": [
552.7586059570312,
174.5865936279297
],
"flags": {},
"order": 21,
"mode": 0,
"inputs": [
{
"name": "source",
"type": "*",
"link": 100
}
],
"outputs": [],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.57",
"Node name for S&R": "PreviewAny",
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.4.1",
"input_ue_unconnectable": {}
}
},
"widgets_values": [
null,
null,
null
]
},
{
"id": 53,
"type": "Reroute",
"pos": [
-2040,
1800
],
"size": [
75,
26
],
"flags": {},
"order": 12,
"mode": 0,
"inputs": [
{
"name": "",
"type": "*",
"link": 253
}
],
"outputs": [
{
"name": "",
"type": "TTS_ENGINE",
"links": [
230
]
}
],
"properties": {
"showOutputText": false,
"horizontal": false,
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.4.1",
"input_ue_unconnectable": {}
}
},
"color": "#222",
"bgcolor": "#000"
},
{
"id": 57,
"type": "MarkdownNote",
"pos": [
-2326.96484375,
1959.491455078125
],
"size": [
343.0154724121094,
178.18296813964844
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [],
"outputs": [],
"properties": {
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.4.1",
"input_ue_unconnectable": {}
}
},
"widgets_values": [
"# **FROM v4 and up!**\n\nUnified nodes:\n- 🎤 **TTS Text**: Direct text-to-speech module \n- 📺 **TTS SRT**: Subtitle-compatible TTS output \n\nThese nodes are now **engine-agnostic**, meaning you can plug in **Chatterbox**, **F5**, or future engines seamlessly.\n"
],
"color": "#432",
"bgcolor": "#653"
},
{
"id": 79,
"type": "PreviewAudio",
"pos": [
-1350,
1800
],
"size": [
441.48828125,
88
],
"flags": {},
"order": 17,
"mode": 4,
"inputs": [
{
"name": "audio",
"type": "AUDIO",
"link": 231
}
],
"outputs": [],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.39",
"Node name for S&R": "PreviewAudio",
"ue_properties": {
"version": "7.4.1",
"widget_ue_connectable": {},
"input_ue_unconnectable": {}
}
},
"widgets_values": [],
"color": "#2a363b",
"bgcolor": "#3f5159"
},
{
"id": 98,
"type": "Reroute",
"pos": [
-2656.391845703125,
876.830322265625
],
"size": [
75,
26
],
"flags": {},
"order": 9,
"mode": 0,
"inputs": [
{
"name": "",
"type": "*",
"widget": {
"name": "value"
},
"link": 244
}
],
"outputs": [
{
"name": "",
"type": "STRING",
"links": [
261
]
}
],
"properties": {
"showOutputText": false,
"horizontal": false,
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.4.1",
"input_ue_unconnectable": {}
}
},
"color": "#232",
"bgcolor": "#353"
},
{
"id": 99,
"type": "Reroute",
"pos": [
-1450,
920
],
"size": [
75,
26
],
"flags": {},
"order": 16,
"mode": 0,
"inputs": [
{
"name": "",
"type": "*",
"widget": {
"name": "value"
},
"link": 227
}
],
"outputs": [
{
"name": "",
"type": "STRING",
"links": [
182
]
}
],
"properties": {
"showOutputText": false,
"horizontal": false,
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.4.1",
"input_ue_unconnectable": {}
}
},
"color": "#232",
"bgcolor": "#353"
},
{
"id": 100,
"type": "Reroute",
"pos": [
-2657.2783203125,
941.9465942382812
],
"size": [
75,
26
],
"flags": {},
"order": 8,
"mode": 0,
"inputs": [
{
"name": "",
"type": "*",
"link": 243
}
],
"outputs": [
{
"name": "",
"type": "STRING",
"links": []
}
],
"properties": {
"showOutputText": false,
"horizontal": false,
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.4.1",
"input_ue_unconnectable": {}
}
},
"color": "#232",
"bgcolor": "#353"
},
{
"id": 115,
"type": "MarkdownNote",
"pos": [
-2630,
1410
],
"size": [
470,
290
],
"flags": {},
"order": 7,
"mode": 0,
"inputs": [],
"outputs": [],
"properties": {
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.4.1",
"input_ue_unconnectable": {}
}
},
"widgets_values": [
" # Higgs Audio v3 - TTS Cloning\n\n Higgs Audio v3 is a native TTS and zero-shot voice cloning engine with official inline paralinguistic tags.\n\n - Check the [Higgs inline tag guide](https://github.com/diodiogod/TTS-Audio-Suite/blob/main/docs/HIGGS_AUDIO_V3_INLINE_TAGS.md)\n - You can also use the Multiline TTS Tag Editor `Inline Tags` tab and select `Higgs Audio v3`\n\n It behaves like any other TTS engine in the suite:\n connect the Engine to the unified `TTS Text` or `TTS SRT` nodes and generate.\n\n Officially, Higgs Audio v3 supports **100+ languages**.\n The public model card lists **102 languages** total.\n\n It does **not** support `🔄 Voice Changer`.\n\n It supports zero-shot cloning with narrator reference audio.\n A matching reference transcript helps cloning consistency, but Higgs Audio v3 does **not** expose a separate language parameter like Qwen3-TTS.\n Language is inferred mainly from the input text.\n\n Higgs Audio v3 supports native inline controls such as:\n\n - `<|emotion:amusement|>`\n - `<|style:whispering|>`\n - `<|prosody:pause|>`\n - `<|sfx:laughter|>`\n\n The suite also accepts alias syntax like `<emotion:amusement>` and rewrites it internally to native Higgs format.\n\n Higgs Audio v3 is not a long-audio dialogue engine like VibeVoice.\n For long TTS, use the unified chunking controls in the `TTS Text` node.\n\n If speech cuts too early, raise `max_new_tokens`.\n For most users, `auto` device, `auto` dtype, and `auto`/`sdpa` attention are the safest defaults."
],
"color": "#432",
"bgcolor": "#653"
},
{
"id": 121,
"type": "PreviewAny",
"pos": [
-1390,
1930
],
"size": [
486.6275634765625,
420.8500061035156
],
"flags": {},
"order": 18,
"mode": 4,
"inputs": [
{
"name": "source",
"type": "*",
"link": 232
}
],
"outputs": [],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.59",
"Node name for S&R": "PreviewAny",
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.4.1",
"input_ue_unconnectable": {}
}
},
"widgets_values": [
null,
null,
null
]
},
{
"id": 132,
"type": "Reroute",
"pos": [
-2500,
920
],
"size": [
75,
26
],
"flags": {},
"order": 13,
"mode": 0,
"inputs": [
{
"name": "",
"type": "*",
"widget": {
"name": "value"
},
"link": 261
}
],
"outputs": [
{
"name": "",
"type": "STRING",
"links": [
227
]
}
],
"properties": {
"showOutputText": false,
"horizontal": false,
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.4.1",
"input_ue_unconnectable": {}
}
},
"color": "#232",
"bgcolor": "#353"
},
{
"id": 133,
"type": "UnifiedTTSSRTNode",
"pos": [
-1850,
1800
],
"size": [
404.7402648925781,
545.216796875
],
"flags": {},
"order": 15,
"mode": 0,
"inputs": [
{
"name": "TTS_engine",
"type": "TTS_ENGINE",
"link": 230
},
{
"name": "opt_narrator",
"shape": 7,
"type": "*",
"link": null
},
{
"name": "srt_content",
"type": "STRING",
"widget": {
"name": "srt_content"
},
"link": 242
}
],
"outputs": [
{
"name": "audio",
"type": "AUDIO",
"links": [
231
]
},
{
"name": "generation_info",
"type": "STRING",
"links": [
232
]
},
{
"name": "timing_report",
"type": "STRING",
"links": null
},
{
"name": "Adjusted_SRT",
"type": "STRING",
"links": null
}
],
"properties": {
"cnr_id": "chatterbox_srt_voice",
"ver": "5e4c39b3d25a437f83dd71cf21b2fad282eda9e1",
"Node name for S&R": "UnifiedTTSSRTNode",
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.4.1",
"input_ue_unconnectable": {}
}
},
"widgets_values": [
"1\n00:00:01,000 --> 00:00:04,000\nHello! This is unified SRT TTS with character switching.\n\n2\n00:00:04,500 --> 00:00:09,500\n[Alice] Hi there! I'm Alice speaking with precise timing.\n\n3\n00:00:10,000 --> 00:00:14,000\n[Bob] And I'm Bob! The audio matches these exact SRT timings.",
"voices_examples/Clint_Eastwood CC3 (enhanced2).wav",
2519695028,
"fixed",
"smart_natural",
true,
0.01,
1,
0.5,
2,
0
],
"color": "#223",
"bgcolor": "#335"
},
{
"id": 139,
"type": "LoadAudio",
"pos": [
-2080,
1230
],
"size": [
270,
136
],
"flags": {},
"order": 5,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "AUDIO",
"type": "AUDIO",
"links": [
258
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.75",
"Node name for S&R": "LoadAudio",
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.4.1",
"input_ue_unconnectable": {}
}
},
"widgets_values": [
"David_Attenborough CC3.wav",
null,
null
],
"color": "#323",
"bgcolor": "#535"
},
{
"id": 140,
"type": "CharacterVoicesNode",
"pos": [
-2050,
1440
],
"size": [
232.96051025390625,
186
],
"flags": {},
"order": 4,
"mode": 0,
"inputs": [
{
"name": "opt_audio_input",
"shape": 7,
"type": "AUDIO",
"link": null
}
],
"outputs": [
{
"name": "opt_narrator",
"type": "NARRATOR_VOICE",
"links": [
235
]
},
{
"name": "character_name",
"type": "STRING",
"links": null
}
],
"properties": {
"cnr_id": "tts_audio_suite",
"ver": "ee95cad1f155eceb1442723c7f351949b30361e3",
"Node name for S&R": "CharacterVoicesNode",
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.4.1",
"input_ue_unconnectable": {}
}
},
"widgets_values": [
"voices_examples/David_Attenborough CC3.wav",
"Type the transcription here",
""
],
"color": "#432",
"bgcolor": "#653"
},
{
"id": 141,
"type": "Reroute",
"pos": [
-1490,
1290
],
"size": [
75,
26
],
"flags": {},
"order": 14,
"mode": 0,
"inputs": [
{
"name": "",
"type": "*",
"link": 265
}
],
"outputs": [
{
"name": "",
"type": "NARRATOR_VOICE",
"links": [
257
]
}
],
"properties": {
"showOutputText": false,
"horizontal": false,
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.4.1",
"input_ue_unconnectable": {}
}
},
"color": "#432",
"bgcolor": "#653"
},
{
"id": 142,
"type": "Reroute",
"pos": [
-1740,
1290
],
"size": [
75,
26
],
"flags": {},
"order": 10,
"mode": 0,
"inputs": [
{
"name": "",
"type": "*",
"link": 235
}
],
"outputs": [
{
"name": "",
"type": "NARRATOR_VOICE",
"links": [
265
]
}
],
"properties": {
"showOutputText": false,
"horizontal": false,
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.4.1",
"input_ue_unconnectable": {}
}
},
"color": "#432",
"bgcolor": "#653"
},
{
"id": 143,
"type": "StringMultilineTagEditor",
"pos": [
-3650,
470
],
"size": [
900,
600
],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "text",
"type": "STRING",
"links": [
244
]
}
],
"properties": {
"cnr_id": "chatterbox_srt_voice",
"ver": "4a9b74fe7c6e1b194b3fffd33b6acca1a199b55f",
"Node name for S&R": "StringMultilineTagEditor",
"ue_properties": {
"widget_ue_connectable": {},
"input_ue_unconnectable": {},
"version": "7.4.1"
},
"ttsTagEditorInlineEngine": "higgs_audio_v3"
},
"widgets_values": [
"On Tuesdays, the pigeons held parliament. [pause:3s] They debated the ethics of breadcrumbs and the metaphysics of flight. One particularly philosophical pigeon named Thistle believed gravity was just a suggestion. He once floated for three minutes straight, fueled by sheer conviction and a gust of rebellious wind."
]
},
{
"id": 146,
"type": "StringMultilineTagEditor",
"pos": [
-3650,
1880
],
"size": [
900,
600
],
"flags": {},
"order": 3,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "text",
"type": "STRING",
"links": [
242
]
}
],
"properties": {
"cnr_id": "chatterbox_srt_voice",
"ver": "4a9b74fe7c6e1b194b3fffd33b6acca1a199b55f",
"Node name for S&R": "StringMultilineTagEditor",
"ue_properties": {
"widget_ue_connectable": {},
"input_ue_unconnectable": {},
"version": "7.4.1"
},
"ttsTagEditorInlineEngine": "higgs_audio_v3"
},
"widgets_values": [
"1\n00:00:01,000 --> 00:00:04,000\n<|emotion:shame|> Hello! <|sfx:sigh|> This is <|sfx:sigh|> unified SRT TTS with character switching.\n\n2\n00:00:04,500 --> 00:00:09,500\n[Alice] <|emotion:surprise|> Hi there! I'm Alice speaking with precise timing.\n\n3\n00:00:10,000 --> 00:00:14,000\n[Bob] <|emotion:surprise|> And I'm Bob! The audio matches these exact SRT timings.\n"
]
},
{
"id": 151,
"type": "StringMultilineTagEditor",
"pos": [
-3650,
1160
],
"size": [
900,
600
],
"flags": {},
"order": 1,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "text",
"type": "STRING",
"links": [
243
]
}
],
"properties": {
"cnr_id": "chatterbox_srt_voice",
"ver": "4a9b74fe7c6e1b194b3fffd33b6acca1a199b55f",
"Node name for S&R": "StringMultilineTagEditor",
"ue_properties": {
"widget_ue_connectable": {},
"input_ue_unconnectable": {},
"version": "7.4.1"
},
"ttsTagEditorInlineEngine": "higgs_audio_v3"
},
"widgets_values": [
"<|emotion:surprise|> On Tuesdays, the pigeons held parliament.\n[Alice] <|emotion:amusement|> They debated the ethics of breadcrumbs and the metaphysics of flight.\n[Bob] <|emotion:confusion|> One particularly philosophical pigeon named Thistle believed gravity was just a suggestion.\n[Cowboy] <|emotion:pride|> He once floated for three minutes straight, fueled by sheer conviction and a gust of rebellious wind."
]
},
{
"id": 153,
"type": "PreviewAudio",
"pos": [
-640,
1110
],
"size": [
540,
88
],
"flags": {},
"order": 20,
"mode": 0,
"inputs": [
{
"name": "audio",
"type": "AUDIO",
"link": 246
}
],
"outputs": [],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.39",
"Node name for S&R": "PreviewAudio",
"ue_properties": {
"version": "7.4.1",
"widget_ue_connectable": {},
"input_ue_unconnectable": {}
}
},
"widgets_values": [],
"color": "#2a363b",
"bgcolor": "#3f5159"
},
{
"id": 156,
"type": "HiggsAudioV3EngineNode",
"pos": [
-2480,
1110
],
"size": [
273.136328125,
226
],
"flags": {},
"order": 6,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "tts_engine",
"type": "TTS_ENGINE",
"links": [
252,
253
]
}
],
"properties": {
"cnr_id": "chatterbox_srt_voice",
"ver": "8760c548d1a76c23665d8d319f092555dd5d0e38",
"Node name for S&R": "HiggsAudioV3EngineNode"
},
"widgets_values": [
"higgs-audio-v3-tts-4b",
"auto",
"auto",
"auto",
1,
0.95,
50,
2048
],
"color": "#222",
"bgcolor": "#000"
},
{
"id": 157,
"type": "Reroute",
"pos": [
-1740,
1230
],
"size": [
75,
26
],
"flags": {},
"order": 11,
"mode": 0,
"inputs": [
{
"name": "",
"type": "*",
"link": 258
}
],
"outputs": [
{
"name": "",
"type": "AUDIO",
"links": []
}
],
"properties": {
"showOutputText": false,
"horizontal": false,
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.4.1",
"input_ue_unconnectable": {}
}
},
"color": "#432",
"bgcolor": "#653"
}
],
"links": [
[
100,
47,
1,
50,
0,
"*"
],
[
182,
99,
0,
47,
2,
"STRING"
],
[
227,
132,
0,
99,
0,
"*"
],
[
230,
53,
0,
133,
0,
"TTS_ENGINE"
],
[
231,
133,
0,
79,
0,
"AUDIO"
],
[
232,
133,
1,
121,
0,
"*"
],
[
235,
140,
0,
142,
0,
"*"
],
[
242,
146,
0,
133,
2,
"STRING"
],
[
243,
151,
0,
100,
0,
"*"
],
[
244,
143,
0,
98,
0,
"*"
],
[
246,
47,
0,
153,
0,
"AUDIO"
],
[
252,
156,
0,
47,
0,
"TTS_ENGINE"
],
[
253,
156,
0,
53,
0,
"TTS_ENGINE"
],
[
257,
141,
0,
47,
1,
"AUDIO"
],
[
258,
139,
0,
157,
0,
"AUDIO"
],
[
261,
98,
0,
132,
0,
"STRING"
],
[
265,
142,
0,
141,
0,
"NARRATOR_VOICE"
]
],
"groups": [
{
"id": 6,
"title": "Simple text exemple",
"bounding": [
-3660,
390,
920,
690
],
"color": "#8A8",
"font_size": 24,
"flags": {}
},
{
"id": 8,
"title": "Multi-char with Native Inline Tags",
"bounding": [
-3660,
1090,
920,
680
],
"color": "#a1309b",
"font_size": 24,
"flags": {}
},
{
"id": 15,
"title": "Basic SRT Exemple",
"bounding": [
-1880,
1720,
986.889892578125,
659.2364501953125
],
"color": "#3f789e",
"font_size": 24,
"flags": {}
},
{
"id": 16,
"title": "⚙️ Engine",
"bounding": [
-2510,
1010,
350,
350
],
"color": "#3f789e",
"font_size": 24,
"flags": {}
},
{
"id": 18,
"title": "TTS TEXT",
"bounding": [
-2140,
1010,
2330,
690
],
"color": "#8A8",
"font_size": 24,
"flags": {}
},
{
"id": 19,
"title": "SRT",
"bounding": [
-3660,
1800,
920,
690
],
"color": "#3f789e",
"font_size": 24,
"flags": {}
}
],
"config": {},
"extra": {
"ds": {
"scale": 0.4240976183724851,
"offset": [
4036.378693654564,
-258.59065864539537
]
},
"frontendVersion": "1.38.13",
"ue_links": [],
"links_added_by_ue": [],
"VHS_latentpreview": true,
"VHS_latentpreviewrate": 0,
"VHS_MetadataImage": true,
"VHS_KeepIntermediate": true,
"workflowRendererVersion": "LG"
},
"version": 0.4
}