工作流 /
音频 /
Chatter Box：支持语音克隆的多语言文本转语音
Chatter Box：支持语音克隆的多语言文本转语音
Chatter Box: Multilingual Text-to-Speech with Voice Cloning
上传一段简短的声音样本并输入您的文本提示词。选择目标语言，使用克隆的参考声音生成多种语言的语音音频。
音频
4 个节点 1 个输入 73 次使用 ComfyUI ≥ 0.25.0 PurzBeats 4 KB
节点构成
LoadAudio
× 1
FL_ChatterboxMultilingualTTS
× 1
MarkdownNote
× 1
SaveAudioMP3
× 1
官方标注的模型
Chatter Box
工作流 JSON
和上面「下载工作流 JSON」是同一份文件。
1{
2 "id": "b2ad020a-8ca3-4e7f-b00d-cb0bead6314d",
3 "revision": 0,
4 "last_node_id": 4,
5 "last_link_id": 2,
6 "nodes": [
7 {
8 "id": 2,
9 "type": "LoadAudio",
10 "pos": [
11 -1519.644153114871,
12 43.941815994044525
13 ],
14 "size": [
15 282.798828125,
16 136
17 ],
18 "flags": [],
19 "order": 0,
20 "mode": 0,
21 "inputs": [],
22 "outputs": [
23 {
24 "name": "AUDIO",
25 "type": "AUDIO",
26 "links": [
27 1
28 ]
29 }
30 ],
31 "properties": {
32 "Node name for S&R": "LoadAudio"
33 },
34 "widgets_values": [
35 "chatterbox_input_target_voice.mp3",
36 null,
37 null
38 ]
39 },
40 {
41 "id": 1,
42 "type": "FL_ChatterboxMultilingualTTS",
43 "pos": [
44 -1200.8165151443131,
45 43.252082165514025
46 ],
47 "size": [
48 405.6428250398121,
49 372.9405024110465
50 ],
51 "flags": [],
52 "order": 2,
53 "mode": 0,
54 "inputs": [
55 {
56 "name": "audio_prompt",
57 "shape": 7,
58 "type": "AUDIO",
59 "link": 1
60 }
61 ],
62 "outputs": [
63 {
64 "name": "audio",
65 "type": "AUDIO",
66 "links": [
67 2
68 ]
69 },
70 {
71 "name": "message",
72 "type": "STRING",
73 "links": null
74 }
75 ],
76 "properties": {
77 "Node name for S&R": "FL_ChatterboxMultilingualTTS"
78 },
79 "widgets_values": [
80 "Hola amigos, bienvenidos de nuevo a ComfyUI.\nHoy vamos a explorar Chatterbox, un flujo de trabajo de clonación de voz capaz de manejar múltiples voces y múltiples idiomas.",
81 "English (en)",
82 0.5,
83 0.5,
84 0.8,
85 2,
86 0.05,
87 1,
88 163260306,
89 "randomize",
90 false,
91 false
92 ]
93 },
94 {
95 "id": 4,
96 "type": "MarkdownNote",
97 "pos": [
98 -1880,
99 40
100 ],
101 "size": [
102 333.4686917593626,
103 391.2736661187166
104 ],
105 "flags": [],
106 "order": 1,
107 "mode": 0,
108 "inputs": [],
109 "outputs": [],
110 "title": "🌍 Chatterbox Multilingual TTS",
111 "properties": [],
112 "widgets_values": [
113 "Generate spoken audio in multiple languages using a voice reference and a text prompt.\n\n---\n\n## How to Use\n\n1. **Load a voice sample** \n Upload a short audio clip into the **Load Audio** node. \n This audio defines the voice that will be used for generation.\n\n2. **Write your prompt** \n Enter the text you want spoken in the **FL Chatterbox Multilingual TTS** node.\n\n3. **Select the language** \n Choose the target language from the **language** dropdown.\n\n4. **Run the workflow** \n Click **Run** to generate the audio.\n\n5. **Listen or export** \n Preview or save the result from **Save Audio (MP3)**.\n\n---\n\n## Notes\n\n- Short, clean voice samples work best \n- The same voice can be used across multiple languages \n- Default settings are a good starting point\n\n---\n"
114 ],
115 "color": "#222",
116 "bgcolor": "#000"
117 },
118 {
119 "id": 3,
120 "type": "SaveAudioMP3",
121 "pos": [
122 -748.4557754373964,
123 43.00134515407583
124 ],
125 "size": [
126 270,
127 136
128 ],
129 "flags": [],
130 "order": 3,
131 "mode": 0,
132 "inputs": [
133 {
134 "name": "audio",
135 "type": "AUDIO",
136 "link": 2
137 }
138 ],
139 "outputs": [],
140 "properties": {
141 "Node name for S&R": "SaveAudioMP3"
142 },
143 "widgets_values": [
144 "audio/ComfyUI",
145 "V0"
146 ]
147 }
148 ],
149 "links": [
150 [
151 1,
152 2,
153 0,
154 1,
155 0,
156 "AUDIO"
157 ],
158 [
159 2,
160 1,
161 0,
162 3,
163 0,
164 "AUDIO"
165 ]
166 ],
167 "groups": [],
168 "config": [],
169 "extra": {
170 "workflowRendererVersion": "LG",
171 "ds": {
172 "scale": 0.9516002317449724,
173 "offset": [
174 1872.693365042086,
175 356.77180684417704
176 ]
177 },
178 "frontendVersion": "1.37.10",
179 "VHS_latentpreview": false,
180 "VHS_latentpreviewrate": 0,
181 "VHS_MetadataImage": true,
182 "VHS_KeepIntermediate": true
183 },
184 "version": 0.4
185}