-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathsynthesize_file.py
99 lines (75 loc) · 3.12 KB
/
synthesize_file.py
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
#!/usr/bin/env python
# Copyright 2018 Google Inc. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""Google Cloud Text-To-Speech API sample application .
Example usage:
python synthesize_file.py --text resources/hello.txt
python synthesize_file.py --ssml resources/hello.ssml
"""
import argparse
import time
from google.cloud import texttospeech
LANG='en-US'
VOICE_NAME='ru-RU-WaveNet-A'
# [START tts_synthesize_text_file]
def synthesize_text_file(text, client, out, lang=LANG):
"""Synthesizes speech from the input file of text."""
input_text = texttospeech.types.SynthesisInput(text=text)
# Note: the voice can also be specified by name.
# Names of voices can be retrieved with client.list_voices().
voice = texttospeech.types.VoiceSelectionParams(
language_code=lang,
name=VOICE_NAME)
audio_config = texttospeech.types.AudioConfig(
audio_encoding=texttospeech.enums.AudioEncoding.MP3)
t1 = time.time()
response = client.synthesize_speech(input_text, voice, audio_config)
# The response's audio_content is binary.
out.write(response.audio_content)
print(time.time() - t1)
# [END tts_synthesize_text_file]
# [START tts_synthesize_ssml_file]
def synthesize_ssml_file(ssml, client, out, lang=LANG):
"""Synthesizes speech from the input file of ssml.
Note: ssml must be well-formed according to:
https://www.w3.org/TR/speech-synthesis/
"""
input_text = texttospeech.types.SynthesisInput(ssml=ssml)
# Note: the voice can also be specified by name.
# Names of voices can be retrieved with client.list_voices().
voice = texttospeech.types.VoiceSelectionParams(
language_code=lang,
name=VOICE_NAME)
audio_config = texttospeech.types.AudioConfig(
audio_encoding=texttospeech.enums.AudioEncoding.MP3)
t1 = time.time()
response = client.synthesize_speech(input_text, voice, audio_config)
# The response's audio_content is binary.
out.write(response.audio_content)
print(time.time() - t1)
# [END tts_synthesize_ssml_file]
if __name__ == '__main__':
parser = argparse.ArgumentParser(
description=__doc__,
formatter_class=argparse.RawDescriptionHelpFormatter)
group = parser.add_mutually_exclusive_group(required=True)
group.add_argument('--text',
help='The text file from which to synthesize speech.')
group.add_argument('--ssml',
help='The ssml file from which to synthesize speech.')
args = parser.parse_args()
if args.text:
synthesize_text_file(args.text)
else:
synthesize_ssml_file(args.ssml)