nodes/diodiogod-TTS-Audio-Suite
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
Files
codex/audio-cpp-integration
diodiogod-TTS-Audio-Suite/example_workflows/Step Audio EditX Integration.json
T
diodiogod 3690fa6829 Version 4.15.0 
Add Step Audio EditX engine and universal inline edit tags

Technical implementation:
- Complete Step Audio EditX TTS and Audio Editor nodes
- Universal inline edit tag post-processing system
- Enhanced Multiline TTS Tag Editor with tabbed interface
- Fix segment grouping and chunk combination parameter bugs
2025-12-12 21:06:07 -03:00

1246 lines
26 KiB
JSON
Raw Permalink Blame History

{
"id": "4a7cdb14-f535-4923-861b-59ba2c7ee043",
"revision": 0,
"last_node_id": 154,
"last_link_id": 248,
"nodes": [
{
"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": []
},
{
"id": 136,
"type": "CharacterVoicesNode",
"pos": [
-1770,
1230
],
"size": [
232.96051025390625,
146.08004760742188
],
"flags": {},
"order": 9,
"mode": 0,
"inputs": [
{
"name": "opt_audio_input",
"shape": 7,
"type": "AUDIO",
"link": 233
}
],
"outputs": [
{
"name": "opt_narrator",
"type": "NARRATOR_VOICE",
"links": [
234
]
},
{
"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": [
"none",
"Type the transcription here"
],
"color": "#432",
"bgcolor": "#653"
},
{
"id": 141,
"type": "Reroute",
"pos": [
-1320,
1230
],
"size": [
75,
26
],
"flags": {},
"order": 14,
"mode": 0,
"inputs": [
{
"name": "",
"type": "*",
"link": 234
}
],
"outputs": [
{
"name": "",
"type": "NARRATOR_VOICE",
"links": null
}
],
"properties": {
"showOutputText": false,
"horizontal": false,
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.4.1",
"input_ue_unconnectable": {}
}
},
"color": "#432",
"bgcolor": "#653"
},
{
"id": 139,
"type": "LoadAudio",
"pos": [
-2080,
1230
],
"size": [
270,
136
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "AUDIO",
"type": "AUDIO",
"links": [
233
]
}
],
"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": [
"Aerith_original.wav",
null,
null
],
"color": "#323",
"bgcolor": "#535"
},
{
"id": 137,
"type": "MarkdownNote",
"pos": [
-1950,
1430
],
"size": [
340,
190
],
"flags": {},
"order": 1,
"mode": 0,
"inputs": [],
"outputs": [],
"properties": {
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.4.1",
"input_ue_unconnectable": {}
}
},
"widgets_values": [
"# 🎭 **Step Audio EditX Reference Audio Tips**\n\n1- You can connect any audio from a **Load Audio Core** node directly on **🎭 Character Voices** and add the transcription manually to make a **zero-shot voice cloning**\n \n2- Step Audio EditX like F5 NEEDS an Audio AND a Reference Text. Any character from **🎭 Character Voices** should have both required files."
],
"color": "#432",
"bgcolor": "#653"
},
{
"id": 142,
"type": "Reroute",
"pos": [
-1320,
1280
],
"size": [
75,
26
],
"flags": {},
"order": 11,
"mode": 0,
"inputs": [
{
"name": "",
"type": "*",
"link": 235
}
],
"outputs": [
{
"name": "",
"type": "NARRATOR_VOICE",
"links": [
237
]
}
],
"properties": {
"showOutputText": false,
"horizontal": false,
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.4.1",
"input_ue_unconnectable": {}
}
},
"color": "#432",
"bgcolor": "#653"
},
{
"id": 134,
"type": "StepAudioEditXEngineNode",
"pos": [
-2470,
1110
],
"size": [
280,
202
],
"flags": {
"collapsed": false
},
"order": 2,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "TTS_engine",
"type": "TTS_ENGINE",
"links": [
238,
239
]
}
],
"properties": {
"cnr_id": "chatterbox_srt_voice",
"ver": "4a9b74fe7c6e1b194b3fffd33b6acca1a199b55f",
"Node name for S&R": "StepAudioEditXEngineNode",
"ue_properties": {
"widget_ue_connectable": {},
"input_ue_unconnectable": {},
"version": "7.4.1"
}
},
"widgets_values": [
"local:Step-Audio-EditX",
"auto",
"bfloat16",
"none",
0.7,
true,
8192
],
"color": "#222",
"bgcolor": "#000"
},
{
"id": 53,
"type": "Reroute",
"pos": [
-2040,
1800
],
"size": [
75,
26
],
"flags": {},
"order": 10,
"mode": 0,
"inputs": [
{
"name": "",
"type": "*",
"link": 239
}
],
"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": 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": 57,
"type": "MarkdownNote",
"pos": [
-2326.96484375,
1959.491455078125
],
"size": [
343.0154724121094,
178.18296813964844
],
"flags": {},
"order": 3,
"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": 146,
"type": "StringMultilineTagEditor",
"pos": [
-3650,
1880
],
"size": [
900,
600
],
"flags": {},
"order": 4,
"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"
}
},
"widgets_values": [
"1\n00:00:01,000 --> 00:00:04,000\nHello! <Breathing:1> This is <Breathing:1> unified SRT TTS with character switching.<emotion:embarrass>\n\n2\n00:00:04,500 --> 00:00:09,500\n[Alice] <Surprise-oh> Hi there! I'm Alice speaking with precise timing.<style:comfort>\n\n3\n00:00:10,000 --> 00:00:14,000\n[Bob] And I'm Bob! The audio matches these exact SRT timings.<style:pure> \n"
]
},
{
"id": 100,
"type": "Reroute",
"pos": [
-2657.2783203125,
941.9465942382812
],
"size": [
75,
26
],
"flags": {},
"order": 12,
"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": 140,
"type": "CharacterVoicesNode",
"pos": [
-1590,
1450
],
"size": [
232.96051025390625,
146.08004760742188
],
"flags": {},
"order": 5,
"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": 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": 47,
"type": "UnifiedTTSTextNode",
"pos": [
-1150,
1110
],
"size": [
400,
379.5921325683594
],
"flags": {},
"order": 20,
"mode": 0,
"inputs": [
{
"name": "TTS_engine",
"type": "TTS_ENGINE",
"link": 238
},
{
"name": "opt_narrator",
"shape": 7,
"type": "*",
"link": 237
},
{
"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": [
-650,
1270
],
"size": [
552.7586059570312,
174.5865936279297
],
"flags": {},
"order": 22,
"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": []
},
{
"id": 98,
"type": "Reroute",
"pos": [
-2656.391845703125,
876.830322265625
],
"size": [
75,
26
],
"flags": {},
"order": 13,
"mode": 0,
"inputs": [
{
"name": "",
"type": "*",
"widget": {
"name": "value"
},
"link": 244
}
],
"outputs": [
{
"name": "",
"type": "STRING",
"links": [
248
]
}
],
"properties": {
"showOutputText": false,
"horizontal": false,
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.4.1",
"input_ue_unconnectable": {}
}
},
"color": "#232",
"bgcolor": "#353"
},
{
"id": 151,
"type": "StringMultilineTagEditor",
"pos": [
-3650,
1160
],
"size": [
900,
600
],
"flags": {},
"order": 6,
"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"
}
},
"widgets_values": [
"On Tuesdays, the pigeons held parliament.<emotion:admiration>\n[Alice] They debated the ethics of breadcrumbs and the metaphysics of flight. <emotion:surprised>\n[Bob] One particularly philosophical pigeon named Thistle believed gravity was just a suggestion.<emotion:confusion>\n[Cowboy] He once floated for three minutes straight, fueled by sheer conviction and a gust of rebellious wind.<emotion:admiration>"
]
},
{
"id": 143,
"type": "StringMultilineTagEditor",
"pos": [
-3650,
470
],
"size": [
900,
600
],
"flags": {},
"order": 7,
"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"
}
},
"widgets_values": [
"On Tuesdays, the pigeons held parliament. [pause:3s] They debated the ethics of breadcrumbs and the metaphysics of flight. \nOne particularly philosophical pigeon named Thistle believed gravity was just a suggestion.\nHe once floated for three minutes straight, fueled by sheer conviction and a gust of rebellious wind."
]
},
{
"id": 153,
"type": "PreviewAudio",
"pos": [
-642.5037841796875,
1109.468994140625
],
"size": [
442.4916687011719,
88
],
"flags": {},
"order": 21,
"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": 132,
"type": "Reroute",
"pos": [
-2500,
920
],
"size": [
75,
26
],
"flags": {},
"order": 16,
"mode": 0,
"inputs": [
{
"name": "",
"type": "*",
"widget": {
"name": "value"
},
"link": 248
}
],
"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": 99,
"type": "Reroute",
"pos": [
-1450,
920
],
"size": [
75,
26
],
"flags": {},
"order": 19,
"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": 115,
"type": "MarkdownNote",
"pos": [
-2650,
1400
],
"size": [
480,
300
],
"flags": {},
"order": 8,
"mode": 0,
"inputs": [],
"outputs": [],
"properties": {
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.4.1",
"input_ue_unconnectable": {}
}
},
"widgets_values": [
"# Step Audio EditX - TTS Cloning\nStep Audio EditX Engine is not only an editing model it is also a cloning voice TTS model.\n\n - Check the other workflow specifically for Edit [and the inline tag guide](https://github.com/diodiogod/TTS-Audio-Suite/blob/main/docs/INLINE_EDIT_TAGS_USER_GUIDE.md)\n \nIt behaves exactly as any other TTS engine. Connect the Engine to Text or SRT unified nodes and generate. \n\nIt officially says it supports languages: Mandarin Chinese (primary), English, Sichuanese, Cantonese, Japanese, Korean\n\nIt does not support '🔄 Voice Changer'.\n\nIt supports zero-shot cloning, but it behaves like F5-TTS in relation to the narrator, it needs a transcription or else it won't work.\n\nStep Audio EditX is not a model that support long audios natively like VibeVoice so you will need chunking for long TTS.\n\nYou can use the quantization option to use less VRAM. Depending on your GPU, it might not support b16, so choose another option."
],
"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,
"*"
],
[
233,
139,
0,
136,
0,
"AUDIO"
],
[
234,
136,
0,
141,
0,
"*"
],
[
235,
140,
0,
142,
0,
"*"
],
[
237,
142,
0,
47,
1,
"*"
],
[
238,
134,
0,
47,
0,
"TTS_ENGINE"
],
[
239,
134,
0,
53,
0,
"*"
],
[
242,
146,
0,
133,
2,
"STRING"
],
[
243,
151,
0,
100,
0,
"*"
],
[
244,
143,
0,
98,
0,
"*"
],
[
246,
47,
0,
153,
0,
"AUDIO"
],
[
248,
98,
0,
132,
0,
"*"
]
],
"groups": [
{
"id": 6,
"title": "Simple text exemple",
"bounding": [
-3660,
390,
920,
690
],
"color": "#8A8",
"font_size": 24,
"flags": {}
},
{
"id": 8,
"title": "Multi-char with [Tags + Second pass Inline Editing]",
"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,
340
],
"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": 0.5283278055000724,
"offset": [
3717.3927365524164,
-316.819467920552
]
},
"frontendVersion": "1.30.6",
"ue_links": [],
"links_added_by_ue": [],
"VHS_latentpreview": true,
"VHS_latentpreviewrate": 0,
"VHS_MetadataImage": true,
"VHS_KeepIntermediate": true
},
"version": 0.4
}
Reference in New Issue View Git Blame Copy Permalink