update: 增加唤醒时声纹处理 ，1秒内发送至大模型 【需优化唤醒锁机制，中途会遭受打断(偶发)，考虑忽略检测】

main/xiaozhi-server/core/providers/tts/linkerai.py

@@ -1,9 +1,7 @@
 import os
-import time
 import queue
 import aiohttp
 import asyncio
-import requests
 import traceback
 from config.logger import setup_logging
 from core.utils.tts import MarkdownCleaner
@@ -111,10 +109,6 @@ class TTSProvider(TTSProviderBase):
         finally:
             return None
 
-    ###################################################################################
-    # linkerai单流式TTS重写父类的方法--结束
-    ###################################################################################
-
     async def text_to_speak(self, text, is_last):
         """流式处理TTS音频，每句只推送一次音频列表"""
         await self._tts_request(text, is_last)
@@ -201,71 +195,3 @@ class TTSProvider(TTSProviderBase):
         except Exception as e:
             logger.bind(tag=TAG).error(f"TTS请求异常: {e}")
             self.tts_audio_queue.put((SentenceType.LAST, [], None))
-
-    def to_tts(self, text: str) -> list:
-        """非流式TTS处理，用于测试及保存音频文件的场景
-        Args:
-            text: 要转换的文本
-        Returns:
-            list: 返回opus编码后的音频数据列表
-        """
-        start_time = time.time()
-        text = MarkdownCleaner.clean_markdown(text)
-
-        params = {
-            "tts_text": text,
-            "spk_id": self.voice,
-            "frame_duration": 60,
-            "stream": False,
-            "target_sr": 16000,
-            "audio_format": self.audio_format,
-            "instruct_text": "请生成一段自然流畅的语音",
-        }
-        headers = {
-            "Authorization": f"Bearer {self.access_token}",
-            "Content-Type": "application/json",
-        }
-
-        try:
-            with requests.get(
-                self.api_url, params=params, headers=headers, timeout=5
-            ) as response:
-                if response.status_code != 200:
-                    logger.bind(tag=TAG).error(
-                        f"TTS请求失败: {response.status_code}, {response.text}"
-                    )
-                    return []
-
-                logger.info(f"TTS请求成功: {text}, 耗时: {time.time() - start_time}秒")
-
-                # 使用opus编码器处理PCM数据
-                opus_datas = []
-                pcm_data = response.content
-
-                # 计算每帧的字节数
-                frame_bytes = int(
-                    self.opus_encoder.sample_rate
-                    * self.opus_encoder.channels
-                    * self.opus_encoder.frame_size_ms
-                    / 1000
-                    * 2
-                )
-
-                # 分帧处理PCM数据
-                for i in range(0, len(pcm_data), frame_bytes):
-                    frame = pcm_data[i : i + frame_bytes]
-                    if len(frame) < frame_bytes:
-                        # 最后一帧可能不足，用0填充
-                        frame = frame + b"\x00" * (frame_bytes - len(frame))
-
-                    self.opus_encoder.encode_pcm_to_opus_stream(
-                        frame,
-                        end_of_stream=(i + frame_bytes >= len(pcm_data)),
-                        callback=lambda opus: opus_datas.append(opus)
-                    )
-
-                return opus_datas
-
-        except Exception as e:
-            logger.bind(tag=TAG).error(f"TTS请求异常: {e}")
-            return []