Ethanfel
8de201a4c9
Two built-in presets, auto-downloaded and cached to ComfyUI/models/omnivoice/presets/: - "Nature – female, warm" (F5-TTS basic_ref_en.wav, transcript included) - "Shadowheart – female, expressive" (Chatterbox demo, connect Whisper for transcript) Outputs ref_audio (AUDIO) and ref_text (STRING) — wire directly into OmniVoice Generate. Updated default workflow to use this node. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
85 lines
2.4 KiB
JSON
85 lines
2.4 KiB
JSON
{
|
||
"last_node_id": 4,
|
||
"last_link_id": 4,
|
||
"nodes": [
|
||
{
|
||
"id": 1,
|
||
"type": "OmniVoiceModelLoader",
|
||
"pos": [40, 80],
|
||
"size": {"0": 300, "1": 100},
|
||
"flags": {},
|
||
"order": 0,
|
||
"mode": 0,
|
||
"outputs": [
|
||
{"name": "model", "type": "OMNIVOICE_MODEL", "links": [1], "shape": 3, "slot_index": 0}
|
||
],
|
||
"properties": {"Node name for S&R": "OmniVoiceModelLoader"},
|
||
"widgets_values": ["cuda:0", "float16"]
|
||
},
|
||
{
|
||
"id": 2,
|
||
"type": "OmniVoiceVoicePreset",
|
||
"pos": [40, 240],
|
||
"size": {"0": 300, "1": 80},
|
||
"flags": {},
|
||
"order": 1,
|
||
"mode": 0,
|
||
"outputs": [
|
||
{"name": "ref_audio", "type": "AUDIO", "links": [2], "shape": 3, "slot_index": 0},
|
||
{"name": "ref_text", "type": "STRING", "links": [3], "shape": 3, "slot_index": 1}
|
||
],
|
||
"properties": {"Node name for S&R": "OmniVoiceVoicePreset"},
|
||
"widgets_values": ["Nature – female, warm (F5-TTS ref)"]
|
||
},
|
||
{
|
||
"id": 3,
|
||
"type": "OmniVoiceGenerate",
|
||
"pos": [420, 80],
|
||
"size": {"0": 380, "1": 310},
|
||
"flags": {},
|
||
"order": 2,
|
||
"mode": 0,
|
||
"inputs": [
|
||
{"name": "model", "type": "OMNIVOICE_MODEL", "link": 1, "slot_index": 0},
|
||
{"name": "ref_audio", "type": "AUDIO", "link": 2, "slot_index": 1},
|
||
{"name": "ref_text", "type": "STRING", "link": 3, "slot_index": 2}
|
||
],
|
||
"outputs": [
|
||
{"name": "audio", "type": "AUDIO", "links": [4], "shape": 3, "slot_index": 0}
|
||
],
|
||
"properties": {"Node name for S&R": "OmniVoiceGenerate"},
|
||
"widgets_values": [
|
||
"Hello! This is a test of the OmniVoice text-to-speech system.",
|
||
"voice_cloning",
|
||
"",
|
||
1.0,
|
||
32
|
||
]
|
||
},
|
||
{
|
||
"id": 4,
|
||
"type": "SaveAudio",
|
||
"pos": [880, 80],
|
||
"size": {"0": 300, "1": 100},
|
||
"flags": {},
|
||
"order": 3,
|
||
"mode": 0,
|
||
"inputs": [
|
||
{"name": "audio", "type": "AUDIO", "link": 4, "slot_index": 0}
|
||
],
|
||
"properties": {"Node name for S&R": "SaveAudio"},
|
||
"widgets_values": ["omnivoice"]
|
||
}
|
||
],
|
||
"links": [
|
||
[1, 1, 0, 3, 0, "OMNIVOICE_MODEL"],
|
||
[2, 2, 0, 3, 1, "AUDIO"],
|
||
[3, 2, 1, 3, 2, "STRING"],
|
||
[4, 3, 0, 4, 0, "AUDIO"]
|
||
],
|
||
"groups": [],
|
||
"config": {},
|
||
"extra": {"ds": {"scale": 0.9, "offset": [0, 0]}},
|
||
"version": 0.4
|
||
}
|