工作流 /
音频 /
ElevenLabs:语音转文本

ElevenLabs:语音转文本
ElevenLabs: Speech to text
上传音频或视频文件,将其语音转录为准确、可编辑的文本。
音频
5 个节点 1 个输入 8 次使用 ComfyUI ≥ 0.15.0 ComfyUI 4 KB
节点构成
PreviewAny
× 2
ElevenLabsSpeechToText
× 1
LoadAudio
× 1
RecordAudio
× 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": 300,
6 "nodes": [
7 {
8 "id": 218,
9 "type": "ElevenLabsSpeechToText",
10 "pos": [
11 2780.6659403747217,
12 1622.666452282765
13 ],
14 "size": [
15 360,
16 452.3125
17 ],
18 "flags": [],
19 "order": 2,
20 "mode": 0,
21 "inputs": [
22 {
23 "name": "audio",
24 "type": "AUDIO",
25 "link": 298
26 }
27 ],
28 "outputs": [
29 {
30 "name": "text",
31 "type": "STRING",
32 "links": [
33 299
34 ]
35 },
36 {
37 "name": "language_code",
38 "type": "STRING",
39 "links": null
40 },
41 {
42 "name": "words_json",
43 "type": "STRING",
44 "links": [
45 300
46 ]
47 }
48 ],
49 "properties": {
50 "cnr_id": "comfy-core",
51 "ver": "0.14.1",
52 "Node name for S&R": "ElevenLabsSpeechToText"
53 },
54 "widgets_values": [
55 "scribe_v2",
56 false,
57 false,
58 0.22,
59 0,
60 "word",
61 "",
62 0,
63 519926995,
64 "randomize"
65 ],
66 "color": "#432",
67 "bgcolor": "#653"
68 },
69 {
70 "id": 219,
71 "type": "LoadAudio",
72 "pos": [
73 2430.666449244203,
74 1622.666647983981
75 ],
76 "size": [
77 282.796875,
78 152
79 ],
80 "flags": [],
81 "order": 0,
82 "mode": 0,
83 "inputs": [],
84 "outputs": [
85 {
86 "name": "AUDIO",
87 "type": "AUDIO",
88 "links": [
89 298
90 ]
91 }
92 ],
93 "properties": {
94 "cnr_id": "comfy-core",
95 "ver": "0.14.1",
96 "Node name for S&R": "LoadAudio"
97 },
98 "widgets_values": [
99 "long_demo.mp3",
100 null,
101 null
102 ]
103 },
104 {
105 "id": 220,
106 "type": "RecordAudio",
107 "pos": [
108 2430.666449244203,
109 1852.666654663298
110 ],
111 "size": [
112 290,
113 132
114 ],
115 "flags": [],
116 "order": 1,
117 "mode": 4,
118 "inputs": [],
119 "outputs": [
120 {
121 "name": "AUDIO",
122 "type": "AUDIO",
123 "links": null
124 }
125 ],
126 "properties": {
127 "cnr_id": "comfy-core",
128 "ver": "0.14.1",
129 "Node name for S&R": "RecordAudio"
130 },
131 "widgets_values": [
132 "",
133 ""
134 ]
135 },
136 {
137 "id": 221,
138 "type": "PreviewAny",
139 "pos": [
140 3200.66638651791,
141 1622.666647983981
142 ],
143 "size": [
144 440,
145 190
146 ],
147 "flags": [],
148 "order": 3,
149 "mode": 0,
150 "inputs": [
151 {
152 "name": "source",
153 "type": "*",
154 "link": 299
155 }
156 ],
157 "outputs": [],
158 "properties": {
159 "cnr_id": "comfy-core",
160 "ver": "0.14.1",
161 "Node name for S&R": "PreviewAny"
162 },
163 "widgets_values": [
164 null,
165 null,
166 false
167 ]
168 },
169 {
170 "id": 222,
171 "type": "PreviewAny",
172 "pos": [
173 3670.6663406057096,
174 1622.666647983981
175 ],
176 "size": [
177 430,
178 490
179 ],
180 "flags": [],
181 "order": 4,
182 "mode": 0,
183 "inputs": [
184 {
185 "name": "source",
186 "type": "*",
187 "link": 300
188 }
189 ],
190 "outputs": [],
191 "title": "words_json",
192 "properties": {
193 "cnr_id": "comfy-core",
194 "ver": "0.14.1",
195 "Node name for S&R": "PreviewAny"
196 },
197 "widgets_values": [
198 null,
199 null,
200 null
201 ]
202 }
203 ],
204 "links": [
205 [
206 298,
207 219,
208 0,
209 218,
210 0,
211 "AUDIO"
212 ],
213 [
214 299,
215 218,
216 0,
217 221,
218 0,
219 "STRING"
220 ],
221 [
222 300,
223 218,
224 2,
225 222,
226 0,
227 "STRING"
228 ]
229 ],
230 "groups": [],
231 "config": [],
232 "extra": {
233 "ds": {
234 "scale": 0.7746100053792364,
235 "offset": [
236 -1476.4595595425485,
237 -1281.613532581446
238 ]
239 },
240 "frontendVersion": "1.39.14",
241 "workflowRendererVersion": "Vue",
242 "ue_links": [],
243 "links_added_by_ue": [],
244 "VHS_latentpreview": false,
245 "VHS_latentpreviewrate": 0,
246 "VHS_MetadataImage": true,
247 "VHS_KeepIntermediate": true
248 },
249 "version": 0.4
250}