Automatically generate Amazon Polly list of voices and regions

homeassistant/components/amazon_polly/const.py

@@ -8,135 +8,32 @@
 CONF_ACCESS_KEY_ID: Final = "aws_access_key_id"
 CONF_SECRET_ACCESS_KEY: Final = "aws_secret_access_key"
 
-DEFAULT_REGION: Final = "us-east-1"
-SUPPORTED_REGIONS: Final[list[str]] = [
-    "us-east-1",
-    "us-east-2",
-    "us-west-1",
-    "us-west-2",
-    "ca-central-1",
-    "eu-west-1",
-    "eu-central-1",
-    "eu-west-2",
-    "eu-west-3",
-    "ap-southeast-1",
-    "ap-southeast-2",
-    "ap-northeast-2",
-    "ap-northeast-1",
-    "ap-south-1",
-    "sa-east-1",
-]
-
 CONF_ENGINE: Final = "engine"
 CONF_VOICE: Final = "voice"
 CONF_OUTPUT_FORMAT: Final = "output_format"
 CONF_SAMPLE_RATE: Final = "sample_rate"
 CONF_TEXT_TYPE: Final = "text_type"
 
-SUPPORTED_VOICES: Final[list[str]] = [
-    "Aditi",  # Hindi
-    "Amy",  # English (British)
-    "Aria",  # English (New Zealand), Neural
-    "Arlet",  # Catalan, Neural
-    "Arthur",  # English, Neural
-    "Astrid",  # Swedish
-    "Ayanda",  # English (South African), Neural
-    "Bianca",  # Italian
-    "Brian",  # English (British)
-    "Camila",  # Portuguese, Brazilian
-    "Carla",  # Italian
-    "Carmen",  # Romanian
-    "Celine",  # French
-    "Chantal",  # French Canadian
-    "Conchita",  # Spanish (European)
-    "Cristiano",  # Portuguese (European)
-    "Daniel",  # German, Neural
-    "Dora",  # Icelandic
-    "Elin",  # Swedish, Neural
-    "Emma",  # English
-    "Enrique",  # Spanish (European)
-    "Ewa",  # Polish
-    "Filiz",  # Turkish
-    "Gabrielle",  # French (Canadian)
-    "Geraint",  # English Welsh
-    "Giorgio",  # Italian
-    "Gwyneth",  # Welsh
-    "Hala",  # Arabic (Gulf), Neural
-    "Hannah",  # German (Austrian), Neural
-    "Hans",  # German
-    "Hiujin",  # Chinese (Cantonese), Neural
-    "Ida",  # Norwegian, Neural
-    "Ines",  # Portuguese, European  # codespell:ignore ines
-    "Ivy",  # English
-    "Jacek",  # Polish
-    "Jan",  # Polish
-    "Joanna",  # English
-    "Joey",  # English
-    "Justin",  # English
-    "Kajal",  # English (Indian)/Hindi (Bilingual ), Neural
-    "Karl",  # Icelandic
-    "Kendra",  # English
-    "Kevin",  # English, Neural
-    "Kimberly",  # English
-    "Laura",  # Dutch, Neural
-    "Lea",  # French
-    "Liam",  # Canadian French, Neural
-    "Liv",  # Norwegian
-    "Lotte",  # Dutch
-    "Lucia",  # Spanish European
-    "Lupe",  # Spanish US
-    "Mads",  # Danish
-    "Maja",  # Polish
-    "Marlene",  # German
-    "Mathieu",  # French
-    "Matthew",  # English
-    "Maxim",  # Russian
-    "Mia",  # Spanish Mexican
-    "Miguel",  # Spanish US
-    "Mizuki",  # Japanese
-    "Naja",  # Danish
-    "Nicole",  # English Australian
-    "Ola",  # Polish, Neural
-    "Olivia",  # Female, Australian, Neural
-    "Penelope",  # Spanish US
-    "Pedro",  # Spanish US, Neural
-    "Raveena",  # English, Indian
-    "Ricardo",  # Portuguese (Brazilian)
-    "Ruben",  # Dutch
-    "Russell",  # English (Australian)
-    "Ruth",  # English, Neural
-    "Salli",  # English
-    "Seoyeon",  # Korean
-    "Stephen",  # English, Neural
-    "Suvi",  # Finnish
-    "Takumi",  # Japanese
-    "Tatyana",  # Russian
-    "Vicki",  # German
-    "Vitoria",  # Portuguese, Brazilian
-    "Zeina",  # Arabic
-    "Zhiyu",  # Chinese
-]
-
-SUPPORTED_OUTPUT_FORMATS: Final[list[str]] = ["mp3", "ogg_vorbis", "pcm"]
+SUPPORTED_OUTPUT_FORMATS: Final[set[str]] = {"mp3", "ogg_vorbis", "pcm"}
 
-SUPPORTED_ENGINES: Final[list[str]] = ["neural", "standard"]
+SUPPORTED_SAMPLE_RATES: Final[set[str]] = {"8000", "16000", "22050", "24000"}
 
-SUPPORTED_SAMPLE_RATES: Final[list[str]] = ["8000", "16000", "22050", "24000"]
-
-SUPPORTED_SAMPLE_RATES_MAP: Final[dict[str, list[str]]] = {
-    "mp3": ["8000", "16000", "22050", "24000"],
-    "ogg_vorbis": ["8000", "16000", "22050"],
-    "pcm": ["8000", "16000"],
+SUPPORTED_SAMPLE_RATES_MAP: Final[dict[str, set[str]]] = {
+    "mp3": {"8000", "16000", "22050", "24000"},
+    "ogg_vorbis": {"8000", "16000", "22050"},
+    "pcm": {"8000", "16000"},
 }
 
-SUPPORTED_TEXT_TYPES: Final[list[str]] = ["text", "ssml"]
+SUPPORTED_TEXT_TYPES: Final[set[str]] = {"text", "ssml"}
 
 CONTENT_TYPE_EXTENSIONS: Final[dict[str, str]] = {
     "audio/mpeg": "mp3",
     "audio/ogg": "ogg",
     "audio/pcm": "pcm",
 }
 
+DEFAULT_REGION: Final = "us-east-1"
+
 DEFAULT_ENGINE: Final = "standard"
 DEFAULT_VOICE: Final = "Joanna"
 DEFAULT_OUTPUT_FORMAT: Final = "mp3"

homeassistant/components/amazon_polly/tts.py

@@ -16,6 +16,11 @@
 )
 from homeassistant.const import ATTR_CREDENTIALS, CONF_PROFILE_NAME
 from homeassistant.core import HomeAssistant
+from homeassistant.generated.amazon_polly import (
+    SUPPORTED_ENGINES,
+    SUPPORTED_REGIONS,
+    SUPPORTED_VOICES,
+)
 import homeassistant.helpers.config_validation as cv
 from homeassistant.helpers.typing import ConfigType, DiscoveryInfoType
 
@@ -38,13 +43,10 @@
     DEFAULT_SAMPLE_RATES,
     DEFAULT_TEXT_TYPE,
     DEFAULT_VOICE,
-    SUPPORTED_ENGINES,
     SUPPORTED_OUTPUT_FORMATS,
-    SUPPORTED_REGIONS,
     SUPPORTED_SAMPLE_RATES,
     SUPPORTED_SAMPLE_RATES_MAP,
     SUPPORTED_TEXT_TYPES,
-    SUPPORTED_VOICES,
 )
 
 _LOGGER: Final = logging.getLogger(__name__)

homeassistant/generated/amazon_polly.py

@@ -0,0 +1,137 @@
+"""Automatically generated file.
+
+To update, run python3 -m script.amazon_polly
+"""
+
+from __future__ import annotations
+
+from typing import Final
+
+SUPPORTED_ENGINES: Final[set[str]] = {
+    "generative",
+    "long-form",
+    "neural",
+    "standard",
+}
+
+SUPPORTED_REGIONS: Final[set[str]] = {
+    "af-south-1",
+    "ap-east-1",
+    "ap-northeast-1",
+    "ap-northeast-2",
+    "ap-northeast-3",
+    "ap-south-1",
+    "ap-southeast-1",
+    "ap-southeast-2",
+    "ca-central-1",
+    "eu-central-1",
+    "eu-north-1",
+    "eu-west-1",
+    "eu-west-2",
+    "eu-west-3",
+    "me-south-1",
+    "sa-east-1",
+    "us-east-1",
+    "us-east-2",
+    "us-west-1",
+    "us-west-2",
+}
+
+SUPPORTED_VOICES: Final[set[str]] = {
+    "Aditi",
+    "Adriano",
+    "Amy",
+    "Andres",
+    "Aria",
+    "Arlet",
+    "Arthur",
+    "Astrid",
+    "Ayanda",
+    "Bianca",
+    "Brian",
+    "Burcu",
+    "Camila",
+    "Carla",
+    "Carmen",
+    "Celine",
+    "Chantal",
+    "Conchita",
+    "Cristiano",
+    "Daniel",
+    "Danielle",
+    "Dora",
+    "Elin",
+    "Emma",
+    "Enrique",
+    "Ewa",
+    "Filiz",
+    "Gabrielle",
+    "Geraint",
+    "Giorgio",
+    "Gregory",
+    "Gwyneth",
+    "Hala",
+    "Hannah",
+    "Hans",
+    "Hiujin",
+    "Ida",
+    "Ines",
+    "Isabelle",
+    "Ivy",
+    "Jacek",
+    "Jan",
+    "Joanna",
+    "Joey",
+    "Justin",
+    "Kajal",
+    "Karl",
+    "Kazuha",
+    "Kendra",
+    "Kevin",
+    "Kimberly",
+    "Laura",
+    "Lea",
+    "Liam",
+    "Lisa",
+    "Liv",
+    "Lotte",
+    "Lucia",
+    "Lupe",
+    "Mads",
+    "Maja",
+    "Marlene",
+    "Mathieu",
+    "Matthew",
+    "Maxim",
+    "Mia",
+    "Miguel",
+    "Mizuki",
+    "Naja",
+    "Niamh",
+    "Nicole",
+    "Ola",
+    "Olivia",
+    "Pedro",
+    "Penelope",
+    "Raveena",
+    "Remi",
+    "Ricardo",
+    "Ruben",
+    "Russell",
+    "Ruth",
+    "Salli",
+    "Seoyeon",
+    "Sergio",
+    "Sofie",
+    "Stephen",
+    "Suvi",
+    "Takumi",
+    "Tatyana",
+    "Thiago",
+    "Tomoko",
+    "Vicki",
+    "Vitoria",
+    "Zayd",
+    "Zeina",
+    "Zhiyu",
+}

script/amazon_polly.py

@@ -0,0 +1,70 @@
+"""Helper script to update supported languages for Amazone Polly text-to-speech (TTS).
+
+N.B. This script requires AWS credentials.
+"""
+
+from dataclasses import dataclass
+from pathlib import Path
+from typing import Self
+
+import boto3
+
+from .hassfest.serializer import format_python_namespace
+
+
+@dataclass(frozen=True)
+class AmazonPollyVoice:
+    """Amazon Polly Voice."""
+
+    id: str
+    name: str
+    gender: str
+    language_name: str
+    language_code: str
+    supported_engines: set[str]
+    additional_language_codes: set[str]
+
+    @classmethod
+    def validate(cls, model: dict[str, str | list[str]]) -> Self:
+        """Validate data model."""
+        return cls(
+            id=model["Id"],
+            name=model["Name"],
+            gender=model["Gender"],
+            language_name=model["LanguageName"],
+            language_code=model["LanguageCode"],
+            supported_engines=set(model["SupportedEngines"]),
+            additional_language_codes=set(model.get("AdditionalLanguageCodes", [])),
+        )
+
+
+def get_all_voices(client: boto3.client) -> list[AmazonPollyVoice]:
+    """Get list of all supported voices from Amazon Polly."""
+    response = client.describe_voices()
+    return [AmazonPollyVoice.validate(voice) for voice in response["Voices"]]
+
+
+supported_regions = set(
+    boto3.session.Session().get_available_regions(service_name="polly")
+)
+
+polly_client = boto3.client(service_name="polly", region_name="us-east-1")
+voices = get_all_voices(polly_client)
+supported_voices = set({v.id for v in voices})
+supported_engines = set().union(*[v.supported_engines for v in voices])
+
+Path("homeassistant/generated/amazon_polly.py").write_text(
+    format_python_namespace(
+        {
+            "SUPPORTED_VOICES": supported_voices,
+            "SUPPORTED_REGIONS": supported_regions,
+            "SUPPORTED_ENGINES": supported_engines,
+        },
+        annotations={
+            "SUPPORTED_VOICES": "Final[set[str]]",
+            "SUPPORTED_REGIONS": "Final[set[str]]",
+            "SUPPORTED_ENGINES": "Final[set[str]]",
+        },
+        generator="script.amazon_polly",
+    )
+)