File size: 20,636 Bytes
960cd20
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
import json
import re
import requests
import os
import time
import random
import string
from requests_toolbelt.multipart.encoder import MultipartEncoder

absolute_path = os.path.dirname(__file__)
base_url = "http://127.0.0.1:23456"


# 映射表
def voice_speakers():
    url = f"{base_url}/voice/speakers"

    res = requests.post(url=url)
    json = res.json()
    for i in json:
        print(i)
        for j in json[i]:
            print(j)
    return json


# 语音合成 voice vits
def voice_vits(text, id=0, format="wav", lang="auto", length=1, noise=0.667, noisew=0.8, segment_size=50,
               save_audio=True,
               save_path=None):
    fields = {
        "text": text,
        "id": str(id),
        "format": format,
        "lang": lang,
        "length": str(length),
        "noise": str(noise),
        "noisew": str(noisew),
        "segment_size": str(segment_size)
    }
    boundary = '----VoiceConversionFormBoundary' + ''.join(random.sample(string.ascii_letters + string.digits, 16))

    m = MultipartEncoder(fields=fields, boundary=boundary)
    headers = {"Content-Type": m.content_type}
    url = f"{base_url}/voice/vits"

    res = requests.post(url=url, data=m, headers=headers)
    fname = re.findall("filename=(.+)", res.headers["Content-Disposition"])[0]
    if save_path is not None:
        path = os.path.join(save_path, fname)
    else:
        path = os.path.join(absolute_path, fname)
    if save_audio:
        with open(path, "wb") as f:
            f.write(res.content)
        print(path)
        return path
    return None


def voice_vits_streaming(text, id=0, format="wav", lang="auto", length=1, noise=0.667, noisew=0.8, segment_size=50,
                         save_audio=True, save_path=None):
    fields = {
        "text": text,
        "id": str(id),
        "format": format,
        "lang": lang,
        "length": str(length),
        "noise": str(noise),
        "noisew": str(noisew),
        "segment_size": str(segment_size),
        "streaming": 'True'
    }
    boundary = '----VoiceConversionFormBoundary' + ''.join(random.sample(string.ascii_letters + string.digits, 16))

    m = MultipartEncoder(fields=fields, boundary=boundary)
    headers = {"Content-Type": m.content_type}
    url = f"{base_url}/voice"

    res = requests.post(url=url, data=m, headers=headers)
    fname = re.findall("filename=(.+)", res.headers["Content-Disposition"])[0]
    if save_path is not None:
        path = os.path.join(save_path, fname)
    else:
        path = os.path.join(absolute_path, fname)
    if save_audio:
        with open(path, "wb") as f:
            f.write(res.content)
        print(path)
        return path
    return None


def voice_vits_streaming(text, id=0, format="wav", lang="auto", length=1, noise=0.667, noisew=0.8, segment_size=50,
                         save_path=None):
    fields = {
        "text": text,
        "id": str(id),
        "format": format,
        "lang": lang,
        "length": str(length),
        "noise": str(noise),
        "noisew": str(noisew),
        "segment_size": str(segment_size),
        "streaming": 'True'
    }
    boundary = '----VoiceConversionFormBoundary' + ''.join(random.sample(string.ascii_letters + string.digits, 16))

    m = MultipartEncoder(fields=fields, boundary=boundary)
    headers = {"Content-Type": m.content_type}
    url = f"{base_url}/voice"

    res = requests.post(url=url, data=m, headers=headers, stream=True)
    fname = re.findall("filename=(.+)", res.headers["Content-Disposition"])[0]
    if save_path is not None:
        path = os.path.join(save_path, fname)
    else:
        path = os.path.join(absolute_path, fname)
    audio = res.content

    def get_file_size_from_bytes(byte_data):
        file_size_offset = 4
        file_size_length = 4

        try:
            file_size_bytes = byte_data[file_size_offset:file_size_offset + file_size_length]
            file_size = int.from_bytes(file_size_bytes, byteorder='little')
            return file_size + 8
        except IndexError:
            return None

    audio = None
    p = 0
    audio_size = None
    audios = []

    for chunk in res.iter_content(chunk_size=1024):
        if audio is None:
            audio = chunk
        else:
            audio += chunk

        p += len(chunk)
        if audio_size is not None:
            if p >= audio_size:
                p = p - audio_size
                audios.append(audio[:audio_size])
                audio = audio[audio_size:]
                audio_size = get_file_size_from_bytes(audio)
        else:
            audio_size = get_file_size_from_bytes(audio)
    for i, audio in enumerate(audios):
        with open(f"{path[:-4]}-{i}.wav", "wb") as f:
            f.write(audio)

        print(f"{path[:-4]}-{i}.wav")
    return path


# 语音转换 hubert-vits
def voice_hubert_vits(upload_path, id, format="wav", length=1, noise=0.667, noisew=0.8, save_audio=True,
                      save_path=None):
    upload_name = os.path.basename(upload_path)
    upload_type = f'audio/{upload_name.split(".")[1]}'  # wav,ogg

    with open(upload_path, 'rb') as upload_file:
        fields = {
            "upload": (upload_name, upload_file, upload_type),
            "id": str(id),
            "format": format,
            "length": str(length),
            "noise": str(noise),
            "noisew": str(noisew),
        }
        boundary = '----VoiceConversionFormBoundary' + ''.join(random.sample(string.ascii_letters + string.digits, 16))

        m = MultipartEncoder(fields=fields, boundary=boundary)
        headers = {"Content-Type": m.content_type}
        url = f"{base_url}/voice/hubert-vits"

        res = requests.post(url=url, data=m, headers=headers)
    fname = re.findall("filename=(.+)", res.headers["Content-Disposition"])[0]
    if save_path is not None:
        path = os.path.join(save_path, fname)
    else:
        path = os.path.join(absolute_path, fname)
    if save_audio:
        with open(path, "wb") as f:
            f.write(res.content)
        print(path)
        return path
    return None


# 维度情感模型 w2v2-vits
def voice_w2v2_vits(text, id=0, format="wav", lang="auto", length=1, noise=0.667, noisew=0.8, segment_size=50,
                    emotion=0,
                    save_audio=True, save_path=None):
    fields = {
        "text": text,
        "id": str(id),
        "format": format,
        "lang": lang,
        "length": str(length),
        "noise": str(noise),
        "noisew": str(noisew),
        "segment_size": str(segment_size),
        "emotion": str(emotion)
    }
    boundary = '----VoiceConversionFormBoundary' + ''.join(random.sample(string.ascii_letters + string.digits, 16))

    m = MultipartEncoder(fields=fields, boundary=boundary)
    headers = {"Content-Type": m.content_type}
    url = f"{base_url}/voice/w2v2-vits"

    res = requests.post(url=url, data=m, headers=headers)
    fname = re.findall("filename=(.+)", res.headers["Content-Disposition"])[0]
    if save_path is not None:
        path = os.path.join(save_path, fname)
    else:
        path = os.path.join(absolute_path, fname)
    if save_audio:
        with open(path, "wb") as f:
            f.write(res.content)
        print(path)
        return path
    return None


# 语音转换 同VITS模型内角色之间的音色转换
def voice_conversion(upload_path, original_id, target_id, save_audio=True, save_path=None):
    upload_name = os.path.basename(upload_path)
    upload_type = f'audio/{upload_name.split(".")[1]}'  # wav,ogg

    with open(upload_path, 'rb') as upload_file:
        fields = {
            "upload": (upload_name, upload_file, upload_type),
            "original_id": str(original_id),
            "target_id": str(target_id),
        }
        boundary = '----VoiceConversionFormBoundary' + ''.join(random.sample(string.ascii_letters + string.digits, 16))
        m = MultipartEncoder(fields=fields, boundary=boundary)

        headers = {"Content-Type": m.content_type}
        url = f"{base_url}/voice/conversion"

        res = requests.post(url=url, data=m, headers=headers)

    fname = re.findall("filename=(.+)", res.headers["Content-Disposition"])[0]
    if save_path is not None:
        path = os.path.join(save_path, fname)
    else:
        path = os.path.join(absolute_path, fname)

    if save_audio:
        with open(path, "wb") as f:
            f.write(res.content)
        print(path)
        return path
    return None


def voice_ssml(ssml, save_audio=True, save_path=None):
    fields = {
        "ssml": ssml,
    }
    boundary = '----VoiceConversionFormBoundary' + ''.join(random.sample(string.ascii_letters + string.digits, 16))

    m = MultipartEncoder(fields=fields, boundary=boundary)
    headers = {"Content-Type": m.content_type}
    url = f"{base_url}/voice/ssml"

    res = requests.post(url=url, data=m, headers=headers)
    fname = re.findall("filename=(.+)", res.headers["Content-Disposition"])[0]
    if save_path is not None:
        path = os.path.join(save_path, fname)
    else:
        path = os.path.join(absolute_path, fname)

    if save_audio:
        with open(path, "wb") as f:
            f.write(res.content)
        print(path)
        return path
    return None


def voice_dimensional_emotion(upload_path, save_audio=True,
                              save_path=None):
    upload_name = os.path.basename(upload_path)
    upload_type = f'audio/{upload_name.split(".")[1]}'  # wav,ogg

    with open(upload_path, 'rb') as upload_file:
        fields = {
            "upload": (upload_name, upload_file, upload_type),
        }
        boundary = '----VoiceConversionFormBoundary' + ''.join(random.sample(string.ascii_letters + string.digits, 16))

        m = MultipartEncoder(fields=fields, boundary=boundary)
        headers = {"Content-Type": m.content_type}
        url = f"{base_url}/voice/dimension-emotion"

        res = requests.post(url=url, data=m, headers=headers)
    fname = re.findall("filename=(.+)", res.headers["Content-Disposition"])[0]
    if save_path is not None:
        path = os.path.join(save_path, fname)
    else:
        path = os.path.join(absolute_path, fname)
    if save_audio:
        with open(path, "wb") as f:
            f.write(res.content)
        print(path)
        return path
    return None


def vits_json(text, id=0, format="wav", lang="auto", length=1, noise=0.667, noisew=0.8, segment_size=50,
              save_audio=True, save_path=None):
    fields = {
        "text": text,
        "id": str(id),
        "format": format,
        "lang": lang,
        "length": str(length),
        "noise": str(noise),
        "noisew": str(noisew),
        "segment_size": str(segment_size)
    }
    f = json.dumps(fields)
    url = f"{base_url}/voice"
    header = {"Content-Type": 'application/json'}
    res = requests.post(url=url, data=f, headers=header)

    fname = re.findall("filename=(.+)", res.headers["Content-Disposition"])[0]
    if save_path is not None:
        path = os.path.join(save_path, fname)
    else:
        path = os.path.join(absolute_path, fname)

    with open(path, "wb") as f:
        f.write(res.content)

    if save_audio:
        with open(path, "wb") as f:
            f.write(res.content)
        print(path)
        return path
    return None


# Bert_vits2
def voice_bert_vits2(text, id=0, format="wav", lang="auto", length=1, noise=0.667, noisew=0.8, segment_size=50,
                     sdp_ratio=0.2, save_audio=True, save_path=None):
    fields = {
        "text": text,
        "id": str(id),
        "format": format,
        "lang": lang,
        "length": str(length),
        "noise": str(noise),
        "noisew": str(noisew),
        "segment_size": str(segment_size),
        "sdp_ratio": str(sdp_ratio)
    }
    boundary = '----VoiceConversionFormBoundary' + ''.join(random.sample(string.ascii_letters + string.digits, 16))

    m = MultipartEncoder(fields=fields, boundary=boundary)
    headers = {"Content-Type": m.content_type}
    url = f"{base_url}/voice/bert-vits2"

    res = requests.post(url=url, data=m, headers=headers)
    fname = re.findall("filename=(.+)", res.headers["Content-Disposition"])[0]
    if save_path is not None:
        path = os.path.join(save_path, fname)
    else:
        path = os.path.join(absolute_path, fname)
    if save_audio:
        with open(path, "wb") as f:
            f.write(res.content)
        print(path)
        return path
    return None


# gpt_sovits
def voice_gpt_sovits(text, id=0, format="wav", lang="auto", preset=None, prompt_text=None, prompt_lang="auto",
                     segment_size=50, reference_audio=None, save_audio=True, save_path=None):
    upload_name, upload_type, upload_file = None, None, None
    if reference_audio is not None:
        upload_name = os.path.basename(reference_audio)
        upload_type = f'audio/{upload_name.split(".")[1]}'
        with open(reference_audio, 'rb') as f:
            upload_file = f.read()

    fields = {
        "text": text,
        "id": str(id),
        "format": format,
        "lang": lang,
        "segment_size": str(segment_size),
        "preset": preset,
        "reference_audio": (upload_name, upload_file, upload_type) if reference_audio else None,
        "prompt_text": prompt_text,
        "prompt_lang": prompt_lang
    }
    boundary = '----VoiceConversionFormBoundary' + ''.join(random.sample(string.ascii_letters + string.digits, 16))

    m = MultipartEncoder(fields=fields, boundary=boundary)
    headers = {"Content-Type": m.content_type}
    url = f"{base_url}/voice/gpt-sovits"

    res = requests.post(url=url, data=m, headers=headers)
    fname = re.findall("filename=(.+)", res.headers["Content-Disposition"])[0]
    if save_path is not None:
        path = os.path.join(save_path, fname)
    else:
        path = os.path.join(absolute_path, fname)
    if save_audio:
        with open(path, "wb") as f:
            f.write(res.content)
        print(path)
        return path
    return None


# Reading
def voice_reading_get(text, in_model_type, in_id, nr_model_type, nr_id, format="wav", lang="auto", preset=None,
                      save_audio=True, save_path=None):
    res = requests.get(
        url=f"{base_url}/voice/reading?text={text}&in_model_type={in_model_type}&in_id={in_id}&preset={preset}&nr_model_type={nr_model_type}&nr_id={nr_id}&lang={lang}&format={format}")

    fname = re.findall("filename=(.+)", res.headers["Content-Disposition"])[0]
    if save_path is not None:
        path = os.path.join(save_path, fname)
    else:
        path = os.path.join(absolute_path, fname)

    with open(path, "wb") as f:
        f.write(res.content)

    if save_audio:
        with open(path, "wb") as f:
            f.write(res.content)
        print(path)
        return path
    return None


# Reading
def voice_reading_json(text, in_model_type, in_id, nr_model_type, nr_id, format="wav", lang="auto", preset=None,
                       save_audio=True, save_path=None):
    fields = {
        "text": text,
        "in_model_type": in_model_type,
        "in_id": str(in_id),
        "nr_model_type": nr_model_type,
        "nr_id": str(nr_id),
        "format": format,
        "lang": lang,
    }
    f = json.dumps(fields)
    url = f"{base_url}/voice/reading"
    header = {"Content-Type": 'application/json'}
    res = requests.post(url=url, data=f, headers=header)

    fname = re.findall("filename=(.+)", res.headers["Content-Disposition"])[0]
    if save_path is not None:
        path = os.path.join(save_path, fname)
    else:
        path = os.path.join(absolute_path, fname)

    with open(path, "wb") as f:
        f.write(res.content)

    if save_audio:
        with open(path, "wb") as f:
            f.write(res.content)
        print(path)
        return path
    return None


# Reading
def voice_reading(text, in_model_type, in_id, nr_model_type, nr_id, format="wav", lang="auto", preset=None,
                  save_audio=True, save_path=None):
    fields = {
        "text": text,
        "in_model_type": in_model_type,
        "in_id": str(in_id),
        "nr_model_type": nr_model_type,
        "nr_id": str(nr_id),
        "format": format,
        "lang": lang,
    }
    boundary = '----VoiceConversionFormBoundary' + ''.join(random.sample(string.ascii_letters + string.digits, 16))

    m = MultipartEncoder(fields=fields, boundary=boundary)
    headers = {"Content-Type": m.content_type}
    url = f"{base_url}/voice/reading"

    res = requests.post(url=url, data=m, headers=headers)
    fname = re.findall("filename=(.+)", res.headers["Content-Disposition"])[0]
    if save_path is not None:
        path = os.path.join(save_path, fname)
    else:
        path = os.path.join(absolute_path, fname)
    if save_audio:
        with open(path, "wb") as f:
            f.write(res.content)
        print(path)
        return path
    return None


def test_interface(text):
    error_num = 0
    for i in range(100):
        try:
            time.sleep(1)
            t1 = time.time()
            voice_vits(text, format="wav", lang="zh", save_audio=False)
            t2 = time.time()
            print(f"{i}:len:{len(text)}耗时:{t2 - t1}")
        except Exception as e:
            error_num += 1
            print(e)
    print(f"error_num={error_num}")


if __name__ == '__main__':
    cache_path = os.path.join(os.path.curdir, "cache")

    text = "你好,こんにちは"

    ssml = """
    <speak lang="zh" format="mp3" length="1.2">
            <voice id="0" model_type="GPT-SOVITS" preset="default">这几天心里颇不宁静。</voice>
            <voice id="0" model_type="Bert-VITS2">今晚在院子里坐着乘凉,忽然想起日日走过的荷塘,在这满月的光里,总该另有一番样子吧。</voice>
            <voice id="142">月亮渐渐地升高了,墙外马路上孩子们的欢笑,已经听不见了;</voice>
            <voice id="0" model_type="Bert-VITS2">妻在屋里拍着闰儿,迷迷糊糊地哼着眠歌。</voice>
            <voice id="120">我悄悄地披了大衫,带上门出去。</voice><break time="2s"/>
            <voice id="121">沿着荷塘,是一条曲折的小煤屑路。</voice>
            <voice id="122">这是一条幽僻的路;白天也少人走,夜晚更加寂寞。</voice>
            <voice id="123">荷塘四面,长着许多树,蓊蓊郁郁的。</voice>
            <voice id="124">路的一旁,是些杨柳,和一些不知道名字的树。</voice>
            <voice id="125">没有月光的晚上,这路上阴森森的,有些怕人。</voice>
            <voice id="126">今晚却很好,虽然月光也还是淡淡的。</voice><break time="2s"/>
            <voice id="127">路上只我一个人,背着手踱着。</voice>
            <voice id="128">这一片天地好像是我的;我也像超出了平常的自己,到了另一个世界里。</voice>
            <voice id="129">我爱热闹,也爱冷静;<break strength="x-weak"/>爱群居,也爱独处。</voice>
            <voice id="130">像今晚上,一个人在这苍茫的月下,什么都可以想,什么都可以不想,便觉是个自由的人。</voice>
            <voice id="131">白天里一定要做的事,一定要说的话,现在都可不理。</voice>
            <voice id="132">这是独处的妙处,我且受用这无边的荷香月色好了。</voice>
        </speak>
    """

    # path = voice_vits(text, save_path=cache_path)
    # path =voice_vits_streaming(text, save_path=cache_path)
    # path = voice_w2v2_vits(text, save_path=cache_path)
    # path = voice_conversion(path, 1, 3, save_path=cache_path)
    # path = voice_hubert_vits(path, 0, save_path=cache_path)
    # path = voice_dimensional_emotion(path, save_path=cache_path)
    # path = voice_ssml(ssml, save_path=cache_path)
    # path = voice_bert_vits2("你好", lang="zh", save_path=cache_path)
    # path = voice_bert_vits2("こんにちは", lang="ja", save_path=cache_path)
    # path = voice_gpt_sovits(text=text, id=2, preset="wz")
    # path = voice_gpt_sovits(text=text, id=2, reference_audio=r"H:\git\vits-simple-api\data\reference_audio\wz_10068.wav",prompt_text="……嗯……大概、快上课的时候开始的。到这个程度的话,……半个小时吧?")

    # os.system(path)

    # text = "你好“你的修炼速度有些出乎我的意料”"
    # path = voice_reading_json(text=text, in_model_type="GPT-SOVITS", preset="wz", in_id=2, nr_model_type="BERT-VITS2",
    #                           nr_id=0)

    # os.system(path)