82 lines
2.7 KiB
Python
82 lines
2.7 KiB
Python
"""Google Text-to-Speech provider."""
|
|
|
|
import asyncio
|
|
import io
|
|
from typing import Any
|
|
|
|
from gtts import gTTS
|
|
|
|
from ..base import TTSProvider
|
|
|
|
|
|
class GTTSProvider(TTSProvider):
|
|
"""Google Text-to-Speech provider implementation."""
|
|
|
|
@property
|
|
def name(self) -> str:
|
|
"""Return the provider name."""
|
|
return "gtts"
|
|
|
|
@property
|
|
def file_extension(self) -> str:
|
|
"""Return the default file extension for this provider."""
|
|
return "mp3"
|
|
|
|
async def generate_speech(self, text: str, **options: Any) -> bytes:
|
|
"""Generate speech from text using Google TTS.
|
|
|
|
Args:
|
|
text: The text to convert to speech
|
|
**options: GTTS-specific options (lang, tld, slow)
|
|
|
|
Returns:
|
|
MP3 audio data as bytes
|
|
|
|
"""
|
|
lang = options.get("lang", "en")
|
|
tld = options.get("tld", "com")
|
|
slow = options.get("slow", False)
|
|
|
|
# Run TTS generation in thread pool since gTTS is synchronous
|
|
def _generate():
|
|
tts = gTTS(text=text, lang=lang, tld=tld, slow=slow)
|
|
fp = io.BytesIO()
|
|
tts.write_to_fp(fp)
|
|
fp.seek(0)
|
|
return fp.read()
|
|
|
|
# Use asyncio.to_thread which is more reliable than run_in_executor
|
|
return await asyncio.to_thread(_generate)
|
|
|
|
def get_supported_languages(self) -> list[str]:
|
|
"""Return list of supported language codes."""
|
|
# Complete list of GTTS supported languages including regional variants
|
|
return [
|
|
"af", "ar", "bg", "bn", "bs", "ca", "cs", "cy", "da", "de", "el",
|
|
"en", "en-au", "en-ca", "en-gb", "en-ie", "en-in", "en-ng", "en-nz",
|
|
"en-ph", "en-za", "en-tz", "en-uk", "en-us",
|
|
"eo", "es", "es-es", "es-mx", "es-us", "et", "eu", "fa", "fi",
|
|
"fr", "fr-ca", "fr-fr", "ga", "gu", "he", "hi", "hr", "hu", "hy",
|
|
"id", "is", "it", "ja", "jw", "ka", "kk", "km", "kn", "ko", "la",
|
|
"lv", "mk", "ml", "mr", "ms", "mt", "my", "ne", "nl", "no", "pa",
|
|
"pl", "pt", "pt-br", "pt-pt", "ro", "ru", "si", "sk", "sl", "sq",
|
|
"sr", "su", "sv", "sw", "ta", "te", "th", "tl", "tr", "uk", "ur",
|
|
"vi", "yo", "zh", "zh-cn", "zh-tw", "zu",
|
|
]
|
|
|
|
def get_option_schema(self) -> dict[str, Any]:
|
|
"""Return schema for GTTS-specific options."""
|
|
return {
|
|
"lang": {
|
|
"type": "string",
|
|
"default": "en",
|
|
"description": "Language code",
|
|
"enum": self.get_supported_languages(),
|
|
},
|
|
"slow": {
|
|
"type": "boolean",
|
|
"default": False,
|
|
"description": "Speak slowly",
|
|
},
|
|
}
|