feat(tts):增加tts（阿里云）提供商CosyVoice TTS(API)，Qwen TTS Realtime(API)的支持，增加过滤 TTS 文本中的内容功能 #7651
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,96 @@ | ||
| """CosyVoice TTS provider using DashScope API. | ||
|
|
||
| Supports models: | ||
| - cosyvoice-v3.5-plus, cosyvoice-v3.5-flash | ||
| - cosyvoice-v3-plus, cosyvoice-v3-flash | ||
| - cosyvoice-v2, cosyvoice-v1 | ||
| - sambert-* models | ||
|
|
||
| Uses dashscope.audio.tts_v2.SpeechSynthesizer for non-streaming TTS. | ||
| """ | ||
|
|
||
| import asyncio | ||
| import os | ||
| import uuid | ||
|
|
||
| from dashscope.audio.tts_v2 import AudioFormat, SpeechSynthesizer | ||
|
Contributor
There was a problem hiding this comment. issue (bug_risk): Guard the CosyVoice DashScope import similarly to the Qwen provider to avoid hard ImportError. This provider imports To align with Qwen and fail gracefully, wrap the import in a |
||
|
|
||
| from astrbot.core import logger | ||
| from astrbot.core.utils.astrbot_path import get_astrbot_temp_path | ||
|
|
||
| from ..entities import ProviderType | ||
| from ..provider import TTSProvider | ||
| from ..register import register_provider_adapter | ||
|
|
||
|
|
||
| @register_provider_adapter( | ||
| "cosyvoice_tts", | ||
| "CosyVoice TTS (DashScope)", | ||
| provider_type=ProviderType.TEXT_TO_SPEECH, | ||
| ) | ||
| class ProviderCosyVoiceTTS(TTSProvider): | ||
| def __init__( | ||
| self, | ||
| provider_config: dict, | ||
| provider_settings: dict, | ||
| ) -> None: | ||
| super().__init__(provider_config, provider_settings) | ||
| self.chosen_api_key: str = provider_config.get("api_key", "") | ||
| self.voice: str = provider_config.get("cosyvoice_voice", "longanyang") | ||
| self.speech_rate: float = provider_config.get("cosyvoice_speech_rate", 1.0) | ||
| self.volume: float = provider_config.get("cosyvoice_volume", 1.0) | ||
| self.pitch_rate: float = provider_config.get("cosyvoice_pitch_rate", 1.0) | ||
| self.timeout_ms: float = float(provider_config.get("timeout", 20)) * 1000 | ||
| self.base_url: str = provider_config.get( | ||
| "cosyvoice_base_url", | ||
| "wss://dashscope.aliyuncs.com/api-ws/v1/inference", | ||
| ) | ||
|
|
||
| model = provider_config.get("model", "cosyvoice-v3-flash") | ||
| self.set_model(model) | ||
|
|
||
| if not self.base_url.startswith("wss://"): | ||
| logger.warning( | ||
| f"[CosyVoice TTS] WebSocket URL 未使用 wss:// 协议: {self.base_url}" | ||
| ) | ||
|
|
||
| async def get_audio(self, text: str) -> str: | ||
| """Synthesize speech using CosyVoice and return the audio file path.""" | ||
| temp_dir = get_astrbot_temp_path() | ||
| os.makedirs(temp_dir, exist_ok=True) | ||
|
|
||
| audio_bytes = await self._synthesize(text) | ||
| if not audio_bytes: | ||
| raise RuntimeError( | ||
| f"Audio synthesis failed for model '{self.get_model()}'. " | ||
| "The model may not be supported or the service is unavailable.", | ||
| ) | ||
|
|
||
| path = os.path.join(temp_dir, f"cosyvoice_tts_{uuid.uuid4()}.wav") | ||
| with open(path, "wb") as f: | ||
| f.write(audio_bytes) | ||
| return path | ||
|
|
||
| async def _synthesize(self, text: str) -> bytes | None: | ||
| """Use CosyVoice SpeechSynthesizer to synthesize speech.""" | ||
| loop = asyncio.get_running_loop() | ||
|
|
||
| model = self.get_model() | ||
| fmt = AudioFormat.WAV_24000HZ_MONO_16BIT | ||
|
|
||
| synthesizer = SpeechSynthesizer( | ||
| model=model, | ||
| voice=self.voice, | ||
| format=fmt, | ||
| api_key=self.chosen_api_key, | ||
| url=self.base_url, | ||
| ) | ||
|
|
||
| audio_bytes = await loop.run_in_executor( | ||
| None, | ||
| synthesizer.call, | ||
| text, | ||
| self.timeout_ms, | ||
| ) | ||
|
|
||
| return audio_bytes | ||
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Uh oh!
There was an error while loading. Please reload this page.