mirror of
https://github.com/xtekky/gpt4free.git
synced 2025-10-31 03:26:22 +08:00
b68b9ff6be
- Added new examples for `client.media.generate` with `PollinationsAI`, `EdgeTTS`, and `Gemini` in `docs/media.md` - Modified `PollinationsAI.py` to default to `default_audio_model` when audio data is present - Adjusted `PollinationsAI.py` to conditionally construct message list from `prompt` when media is being generated - Rearranged `PollinationsAI.py` response handling to yield `save_response_media` after checking for non-JSON content types - Added support in `EdgeTTS.py` to use default values for `language`, `locale`, and `format` from class attributes - Improved voice selection logic in `EdgeTTS.py` to fallback to default locale or language when not explicitly provided - Updated `EdgeTTS.py` to yield `AudioResponse` with `text` field included - Modified `Gemini.py` to support `.ogx` audio generation when `model == "gemini-audio"` or `audio` is passed - Used `format_image_prompt` in `Gemini.py` to create audio prompt and saved audio file using `synthesize` - Appended `AudioResponse` to `Gemini.py` for audio generation flow - Added `save()` method to `Image` class in `stubs.py` to support saving `/media/` files locally - Changed `client/__init__.py` to fallback to `options["text"]` if `alt` is missing in `Images.create` - Ensured `AudioResponse` in `copy_images.py` includes the `text` (prompt) field - Added `Annotated` fallback definition in `api/__init__.py` for compatibility with older Python versions
73 lines
2.7 KiB
Python
73 lines
2.7 KiB
Python
from __future__ import annotations
|
|
|
|
import os
|
|
import random
|
|
import asyncio
|
|
|
|
try:
|
|
import edge_tts
|
|
from edge_tts import VoicesManager
|
|
has_edge_tts = True
|
|
except ImportError:
|
|
has_edge_tts = False
|
|
|
|
from ...typing import AsyncResult, Messages
|
|
from ...providers.response import AudioResponse
|
|
from ...image.copy_images import get_filename, get_media_dir, ensure_media_dir
|
|
from ..base_provider import AsyncGeneratorProvider, ProviderModelMixin
|
|
from ..helper import format_image_prompt
|
|
|
|
class EdgeTTS(AsyncGeneratorProvider, ProviderModelMixin):
|
|
label = "Edge TTS"
|
|
working = has_edge_tts
|
|
default_language = "en"
|
|
default_locale = "en-US"
|
|
default_format = "mp3"
|
|
|
|
@classmethod
|
|
def get_models(cls) -> list[str]:
|
|
if not cls.models:
|
|
voices = asyncio.run(VoicesManager.create())
|
|
cls.default_model = voices.find(Locale=cls.default_locale)[0]["Name"]
|
|
cls.models = [voice["Name"] for voice in voices.voices]
|
|
return cls.models
|
|
|
|
@classmethod
|
|
async def create_async_generator(
|
|
cls,
|
|
model: str,
|
|
messages: Messages,
|
|
proxy: str = None,
|
|
prompt: str = None,
|
|
audio: dict = {},
|
|
**kwargs
|
|
) -> AsyncResult:
|
|
prompt = format_image_prompt(messages, prompt)
|
|
if not prompt:
|
|
raise ValueError("Prompt is empty.")
|
|
voice = audio.get("voice", model if model and model != "edge-tts" else None)
|
|
if not voice:
|
|
voices = await VoicesManager.create()
|
|
if "locale" in audio:
|
|
voices = voices.find(Locale=audio["locale"])
|
|
elif audio.get("language", cls.default_language) != cls.default_language:
|
|
if "-" in audio.get("language"):
|
|
voices = voices.find(Locale=audio.get("language"))
|
|
else:
|
|
voices = voices.find(Language=audio.get("language"))
|
|
else:
|
|
voices = voices.find(Locale=cls.default_locale)
|
|
if not voices:
|
|
raise ValueError(f"No voices found for language '{audio.get('language')}' and locale '{audio.get('locale')}'.")
|
|
voice = random.choice(voices)["Name"]
|
|
|
|
format = audio.get("format", cls.default_format)
|
|
filename = get_filename([cls.default_model], prompt, f".{format}", prompt)
|
|
target_path = os.path.join(get_media_dir(), filename)
|
|
ensure_media_dir()
|
|
|
|
extra_parameters = {param: audio[param] for param in ["rate", "volume", "pitch"] if param in audio}
|
|
communicate = edge_tts.Communicate(prompt, voice=voice, proxy=proxy, **extra_parameters)
|
|
|
|
await communicate.save(target_path)
|
|
yield AudioResponse(f"/media/{filename}", voice=voice, text=prompt) |