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
|
#!/usr/bin/python3
"""Update the voice data."""
# ruff: noqa: T201
import asyncio
from pathlib import Path
import subprocess
import aiohttp
voice_data_path = Path(__file__).parent.parent / "hass_nabucasa/voice_data.py"
REGION = "westus"
LIST_VOICES_URL = (
f"https://{REGION}.tts.speech.microsoft.com/cognitiveservices/voices/list"
)
def main() -> None:
"""Run script."""
token = None
while not token:
token = input("Please enter your Azure token: ").strip()
raw_data = asyncio.run(get_data(token))
data = {}
for voice in raw_data:
if voice["Status"] != "GA":
continue
locale = voice["Locale"]
voice_id = voice["ShortName"][len(locale) + 1 :]
voice_name = voice["DisplayName"]
if voice_name.endswith("Neural"):
voice_name = voice_name[:-7].strip()
# Skip variants
if ":" in voice_id or "Multilingual" in voice_id:
continue
voice_info = {
"name": voice_name,
}
if style_list := voice.get("StyleList"):
voice_info = {
"name": voice_name,
"variants": style_list,
}
else:
voice_info = voice_name
data.setdefault(locale, {})[voice_id] = voice_info
# Sort the data
for locale, info in data.items():
data[locale] = dict(
sorted(
info.items(),
key=lambda x: x[1]["name"] if isinstance(x[1], dict) else x[1],
)
)
data = dict(sorted(data.items()))
parts = [
'"""',
"Available voices for TTS.",
"",
"Automatically generated file, do not edit this file directly.",
"Run python3 -m scripts/update_voice_data.py to update this file.",
'"""',
"",
f"TTS_VOICES: dict[str, dict[str, dict | str]] = {data}",
]
voice_data_path.write_text("\n".join(parts))
subprocess.run( # noqa: S603
["ruff", "format", voice_data_path], # noqa: S607
check=True,
stdout=subprocess.DEVNULL,
)
print("Updated voice_data.py with new voice data.")
async def get_data(token: str) -> dict:
"""Gather data."""
async with aiohttp.ClientSession() as session:
voices = await session.get(
LIST_VOICES_URL, headers={"Authorization": f"Bearer {token}"}
)
voices.raise_for_status()
return await voices.json()
if __name__ == "__main__":
main()
|
