工作流 /
音频 /
ElevenLabs：语音转语音
ElevenLabs：语音转语音
ElevenLabs: Speech to Speech
上传源音频文件以应用新的语音语调或克隆不同的声音，生成修改后的音频输出。
音频
8 个节点 2 个输入 23 次使用 ComfyUI ≥ 0.25.0 ComfyUI 8 KB
节点构成
LoadAudio
× 2
ElevenLabsInstantVoiceClone
× 1
Note
× 1
RecordAudio
× 1
ElevenLabsVoiceSelector
× 1
ElevenLabsSpeechToSpeech
× 1
SaveAudioAdvanced
× 1
官方标注的模型
ElevenLabs
工作流 JSON
和上面「下载工作流 JSON」是同一份文件。
1{
2 "id": "91f6bbe2-ed41-4fd6-bac7-71d5b5864ecb",
3 "revision": 0,
4 "last_node_id": 222,
5 "last_link_id": 305,
6 "nodes": [
7 {
8 "id": 210,
9 "type": "LoadAudio",
10 "pos": [
11 1810,
12 1110
13 ],
14 "size": [
15 240,
16 170
17 ],
18 "flags": [],
19 "order": 0,
20 "mode": 4,
21 "inputs": [],
22 "outputs": [
23 {
24 "name": "AUDIO",
25 "type": "AUDIO",
26 "links": [
27 296
28 ]
29 }
30 ],
31 "properties": {
32 "Node name for S&R": "LoadAudio",
33 "cnr_id": "comfy-core",
34 "ver": "0.14.1"
35 },
36 "widgets_values": [
37 "long_demo.mp3",
38 null,
39 null
40 ],
41 "widgets_values_named": {
42 "audio": "long_demo.mp3",
43 "upload": null
44 }
45 },
46 {
47 "id": 212,
48 "type": "ElevenLabsInstantVoiceClone",
49 "pos": [
50 2100,
51 1110
52 ],
53 "size": [
54 270,
55 110
56 ],
57 "flags": [],
58 "order": 5,
59 "mode": 4,
60 "inputs": [
61 {
62 "label": "audio0",
63 "name": "files.audio0",
64 "type": "AUDIO",
65 "link": 296
66 },
67 {
68 "name": "files.audio1",
69 "shape": 7,
70 "type": "AUDIO",
71 "link": null
72 }
73 ],
74 "outputs": [
75 {
76 "name": "voice",
77 "type": "ELEVENLABS_VOICE",
78 "links": null
79 }
80 ],
81 "properties": {
82 "Node name for S&R": "ElevenLabsInstantVoiceClone",
83 "cnr_id": "comfy-core",
84 "ver": "0.14.1"
85 },
86 "widgets_values": [
87 true
88 ],
89 "widgets_values_named": {
90 "remove_background_noise": true
91 },
92 "color": "#432",
93 "bgcolor": "#653"
94 },
95 {
96 "id": 217,
97 "type": "Note",
98 "pos": [
99 2110,
100 1280
101 ],
102 "size": [
103 260,
104 110
105 ],
106 "flags": [],
107 "order": 1,
108 "mode": 0,
109 "inputs": [],
110 "outputs": [],
111 "title": "How to enable bypassed nodes",
112 "properties": [],
113 "widgets_values": [
114 "Please select and use Ctrl-B to enable the bypassed nodes."
115 ],
116 "widgets_values_named": {
117 "text": "Please select and use Ctrl-B to enable the bypassed nodes."
118 },
119 "color": "#222",
120 "bgcolor": "#653"
121 },
122 {
123 "id": 214,
124 "type": "RecordAudio",
125 "pos": [
126 1810,
127 1340
128 ],
129 "size": [
130 240,
131 150
132 ],
133 "flags": [],
134 "order": 2,
135 "mode": 4,
136 "inputs": [],
137 "outputs": [
138 {
139 "name": "AUDIO",
140 "type": "AUDIO",
141 "links": null
142 }
143 ],
144 "properties": {
145 "Node name for S&R": "RecordAudio",
146 "cnr_id": "comfy-core",
147 "ver": "0.14.1"
148 },
149 "widgets_values": [
150 "",
151 ""
152 ],
153 "widgets_values_named": {
154 "audio": ""
155 }
156 },
157 {
158 "id": 219,
159 "type": "ElevenLabsVoiceSelector",
160 "pos": [
161 1920,
162 900
163 ],
164 "size": [
165 320,
166 90
167 ],
168 "flags": [],
169 "order": 3,
170 "mode": 0,
171 "inputs": [],
172 "outputs": [
173 {
174 "name": "voice",
175 "type": "ELEVENLABS_VOICE",
176 "links": [
177 302
178 ]
179 }
180 ],
181 "properties": {
182 "Node name for S&R": "ElevenLabsVoiceSelector",
183 "cnr_id": "comfy-core",
184 "ver": "0.14.1"
185 },
186 "widgets_values": [
187 "Jessica (female, american)"
188 ],
189 "widgets_values_named": {
190 "voice": "Jessica (female, american)"
191 }
192 },
193 {
194 "id": 220,
195 "type": "ElevenLabsSpeechToSpeech",
196 "pos": [
197 2460,
198 630
199 ],
200 "size": [
201 320,
202 350
203 ],
204 "flags": [],
205 "order": 6,
206 "mode": 0,
207 "inputs": [
208 {
209 "name": "voice",
210 "type": "ELEVENLABS_VOICE",
211 "link": 302
212 },
213 {
214 "name": "audio",
215 "type": "AUDIO",
216 "link": 303
217 }
218 ],
219 "outputs": [
220 {
221 "name": "AUDIO",
222 "type": "AUDIO",
223 "links": [
224 305
225 ]
226 }
227 ],
228 "properties": {
229 "Node name for S&R": "ElevenLabsSpeechToSpeech",
230 "cnr_id": "comfy-core",
231 "ver": "0.14.1"
232 },
233 "widgets_values": [
234 0.5,
235 "eleven_multilingual_sts_v2",
236 1,
237 0.75,
238 false,
239 0,
240 "mp3_44100_192",
241 672717223,
242 "randomize",
243 false
244 ],
245 "widgets_values_named": {
246 "stability": 0.5,
247 "model": "eleven_multilingual_sts_v2",
248 "model.speed": 1,
249 "model.similarity_boost": 0.75,
250 "model.use_speaker_boost": false,
251 "model.style": 0,
252 "output_format": "mp3_44100_192",
253 "seed": 672717223,
254 "control_after_generate": "randomize",
255 "remove_background_noise": false
256 },
257 "color": "#432",
258 "bgcolor": "#653"
259 },
260 {
261 "id": 221,
262 "type": "LoadAudio",
263 "pos": [
264 1840,
265 650
266 ],
267 "size": [
268 490,
269 170
270 ],
271 "flags": [],
272 "order": 4,
273 "mode": 0,
274 "inputs": [],
275 "outputs": [
276 {
277 "name": "AUDIO",
278 "type": "AUDIO",
279 "links": [
280 303
281 ]
282 }
283 ],
284 "properties": {
285 "Node name for S&R": "LoadAudio",
286 "cnr_id": "comfy-core",
287 "ver": "0.14.1"
288 },
289 "widgets_values": [
290 "api_elevenlabs_speech_to_speech.mp3",
291 null,
292 null
293 ],
294 "widgets_values_named": {
295 "audio": "api_elevenlabs_speech_to_speech.mp3",
296 "upload": null
297 }
298 },
299 {
300 "id": 222,
301 "type": "SaveAudioAdvanced",
302 "pos": [
303 2820,
304 630
305 ],
306 "size": [
307 680,
308 178
309 ],
310 "flags": [],
311 "order": 7,
312 "mode": 0,
313 "inputs": [
314 {
315 "name": "audio",
316 "type": "AUDIO",
317 "link": 305
318 }
319 ],
320 "outputs": [
321 {
322 "name": "audio",
323 "type": "AUDIO",
324 "links": null
325 }
326 ],
327 "properties": [],
328 "widgets_values": [
329 "audio/ComfyUI",
330 "mp3",
331 "V0"
332 ],
333 "widgets_values_named": {
334 "filename_prefix": "audio/ComfyUI",
335 "format": "mp3",
336 "format.quality": "V0"
337 }
338 }
339 ],
340 "links": [
341 [
342 296,
343 210,
344 0,
345 212,
346 0,
347 "AUDIO"
348 ],
349 [
350 302,
351 219,
352 0,
353 220,
354 0,
355 "ELEVENLABS_VOICE"
356 ],
357 [
358 303,
359 221,
360 0,
361 220,
362 1,
363 "AUDIO"
364 ],
365 [
366 305,
367 220,
368 0,
369 222,
370 0,
371 "AUDIO"
372 ]
373 ],
374 "groups": [
375 {
376 "id": 1,
377 "title": "Option 2: Create a Voice Clone",
378 "bounding": [
379 1780,
380 1040,
381 610,
382 470
383 ],
384 "color": "#3f789e",
385 "flags": []
386 },
387 {
388 "id": 2,
389 "title": "Option 1: Use Preset Voice",
390 "bounding": [
391 1780,
392 830,
393 610,
394 180
395 ],
396 "color": "#3f789e",
397 "flags": []
398 },
399 {
400 "id": 3,
401 "title": "Source Audio",
402 "bounding": [
403 1780,
404 580,
405 610,
406 220
407 ],
408 "color": "#3f789e",
409 "flags": []
410 }
411 ],
412 "config": [],
413 "extra": {
414 "ds": {
415 "scale": 0.8115168539325842,
416 "offset": [
417 -1663.5564317237793,
418 -263.5569184839044
419 ]
420 },
421 "frontendVersion": "1.52.5",
422 "workflowRendererVersion": "LG",
423 "ue_links": [],
424 "links_added_by_ue": [],
425 "VHS_latentpreview": false,
426 "VHS_latentpreviewrate": 0,
427 "VHS_MetadataImage": true,
428 "VHS_KeepIntermediate": true
429 },
430 "version": 0.4
431}