update: 更改to_tts保存临时文件判断

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

@@ -91,7 +91,7 @@ class TTSProvider(TTSProviderBase):
 
         self.appkey = config.get("appkey")
         self.format = config.get("format", "wav")
-
+        self.audio_file_type = config.get("format", "wav")
         sample_rate = config.get("sample_rate", "16000")
         self.sample_rate = int(sample_rate) if sample_rate else 16000
 
@@ -188,9 +188,12 @@ class TTSProvider(TTSProviderBase):
                 )
             # 检查返回请求数据的mime类型是否是audio/***，是则保存到指定路径下；返回的是binary格式的
             if resp.headers["Content-Type"].startswith("audio/"):
-                with open(output_file, "wb") as f:
-                    f.write(resp.content)
-                return output_file
+                if output_file:
+                    with open(output_file, "wb") as f:
+                        f.write(resp.content)
+                    return output_file
+                else:
+                    return resp.content
             else:
                 raise Exception(
                     f"{__name__} status_code: {resp.status_code} response: {resp.content}"

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

@@ -8,7 +8,7 @@ from datetime import datetime
 from core.utils import textUtils
 from abc import ABC, abstractmethod
 from config.logger import setup_logging
-from core.utils.util import audio_to_data
+from core.utils.util import audio_to_data, audio_bytes_to_data
 from core.utils.tts import MarkdownCleaner
 from core.utils.output_counter import add_device_output
 from core.handle.reportHandle import enqueue_tts_report
@@ -20,7 +20,6 @@ from core.providers.tts.dto.dto import (
     InterfaceType,
 )
 
-
 import traceback
 
 TAG = __name__
@@ -33,6 +32,7 @@ class TTSProviderBase(ABC):
         self.conn = None
         self.tts_timeout = 10
         self.delete_audio_file = delete_audio_file
+        self.audio_file_type = "wav"
         self.output_file = config.get("output_dir", "tmp/")
         self.tts_text_queue = queue.Queue()
         self.tts_audio_queue = queue.Queue()
@@ -76,35 +76,60 @@ class TTSProviderBase(ABC):
         )
 
     def to_tts(self, text):
-        tmp_file = self.generate_filename()
-        try:
-            max_repeat_time = 5
-            text = MarkdownCleaner.clean_markdown(text)
-            while not os.path.exists(tmp_file) and max_repeat_time > 0:
+        text = MarkdownCleaner.clean_markdown(text)
+        max_repeat_time = 5
+        if self.delete_audio_file:
+            # 需要删除文件的直接转为音频数据
+            while max_repeat_time > 0:
                 try:
-                    asyncio.run(self.text_to_speak(text, tmp_file))
+                    audio_bytes = asyncio.run(self.text_to_speak(text, None))
+                    if audio_bytes:
+                        audio_datas, _ = audio_bytes_to_data(audio_bytes, file_type=self.audio_file_type, is_opus=True)
+                        return audio_datas
+                    else:
+                        max_repeat_time -= 1
                 except Exception as e:
                     logger.bind(tag=TAG).warning(
                         f"语音生成失败{5 - max_repeat_time + 1}次: {text}，错误: {e}"
                     )
-                    # 未执行成功，删除文件
-                    if os.path.exists(tmp_file):
-                        os.remove(tmp_file)
                     max_repeat_time -= 1
-
             if max_repeat_time > 0:
                 logger.bind(tag=TAG).info(
-                    f"语音生成成功: {text}:{tmp_file}，重试{5 - max_repeat_time}次"
+                    f"语音生成成功: {text}，重试{5 - max_repeat_time}次"
                 )
             else:
                 logger.bind(tag=TAG).error(
                     f"语音生成失败: {text}，请检查网络或服务是否正常"
                 )
-
-            return tmp_file
-        except Exception as e:
-            logger.bind(tag=TAG).error(f"Failed to generate TTS file: {e}")
             return None
+        else:
+            tmp_file = self.generate_filename()
+            try:
+                while not os.path.exists(tmp_file) and max_repeat_time > 0:
+                    try:
+                        asyncio.run(self.text_to_speak(text, tmp_file))
+                    except Exception as e:
+                        logger.bind(tag=TAG).warning(
+                            f"语音生成失败{5 - max_repeat_time + 1}次: {text}，错误: {e}"
+                        )
+                        # 未执行成功，删除文件
+                        if os.path.exists(tmp_file):
+                            os.remove(tmp_file)
+                        max_repeat_time -= 1
+
+                if max_repeat_time > 0:
+                    logger.bind(tag=TAG).info(
+                        f"语音生成成功: {text}:{tmp_file}，重试{5 - max_repeat_time}次"
+                    )
+                else:
+                    logger.bind(tag=TAG).error(
+                        f"语音生成失败: {text}，请检查网络或服务是否正常"
+                    )
+
+                return tmp_file
+            except Exception as e:
+                logger.bind(tag=TAG).error(f"Failed to generate TTS file: {e}")
+                return None
 
     @abstractmethod
     async def text_to_speak(self, text, output_file):
@@ -192,12 +217,19 @@ class TTSProviderBase(ABC):
                     self.tts_text_buff.append(message.content_detail)
                     segment_text = self._get_segment_text()
                     if segment_text:
-                        tts_file = self.to_tts(segment_text)
-                        if tts_file:
-                            audio_datas = self._process_audio_file(tts_file)
-                            self.tts_audio_queue.put(
-                                (message.sentence_type, audio_datas, segment_text)
-                            )
+                        if self.delete_audio_file:
+                            audio_datas = self.to_tts(segment_text)
+                            if audio_datas:
+                                self.tts_audio_queue.put(
+                                    (message.sentence_type, audio_datas, segment_text)
+                                )
+                        else:
+                            tts_file = self.to_tts(segment_text)
+                            if tts_file:
+                                audio_datas = self._process_audio_file(tts_file)
+                                self.tts_audio_queue.put(
+                                    (message.sentence_type, audio_datas, segment_text)
+                                )
                 elif ContentType.FILE == message.content_type:
                     self._process_remaining_text()
                     tts_file = message.content_file
@@ -334,11 +366,18 @@ class TTSProviderBase(ABC):
         if remaining_text:
             segment_text = textUtils.get_string_no_punctuation_or_emoji(remaining_text)
             if segment_text:
-                tts_file = self.to_tts(segment_text)
-                audio_datas = self._process_audio_file(tts_file)
-                self.tts_audio_queue.put(
-                    (SentenceType.MIDDLE, audio_datas, segment_text)
-                )
+                if self.delete_audio_file:
+                    audio_datas = self.to_tts(segment_text)
+                    if audio_datas:
+                        self.tts_audio_queue.put(
+                            (SentenceType.MIDDLE, audio_datas, segment_text)
+                        )
+                else:
+                    tts_file = self.to_tts(segment_text)
+                    audio_datas = self._process_audio_file(tts_file)
+                    self.tts_audio_queue.put(
+                        (SentenceType.MIDDLE, audio_datas, segment_text)
+                    )
                 self.processed_chars += len(full_text)
                 return True
         return False

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

@@ -11,8 +11,8 @@ class TTSProvider(TTSProviderBase):
             self.voice = config.get("private_voice")
         else:
             self.voice = config.get("voice")
-        self.response_format = config.get("response_format")
-
+        self.response_format = config.get("response_format", "mp3")
+        self.audio_file_type = config.get("response_format", "mp3")
         self.host = "api.coze.cn"
         self.api_url = f"https://{self.host}/v1/audio/speech"
 
@@ -33,7 +33,10 @@ class TTSProvider(TTSProviderBase):
                 "POST", self.api_url, json=request_json, headers=headers
             )
             data = response.content
-            file_to_save = open(output_file, "wb")
-            file_to_save.write(data)
+            if output_file:
+                with open(output_file, "wb") as file_to_save:
+                    file_to_save.write(data)
+            else:
+                return data
         except Exception as e:
             raise Exception(f"{__name__} error: {e}")

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

@@ -16,8 +16,8 @@ class TTSProvider(TTSProviderBase):
         self.method = config.get("method", "GET")
         self.headers = config.get("headers", {})
         self.format = config.get("format", "wav")
+        self.audio_file_type = config.get("format", "wav")
         self.output_file = config.get("output_dir", "tmp/")
-
         self.params = config.get("params")
 
         if isinstance(self.params, str):
@@ -43,8 +43,11 @@ class TTSProvider(TTSProviderBase):
         else:
             resp = requests.get(self.url, params=request_params, headers=self.headers)
         if resp.status_code == 200:
-            with open(output_file, "wb") as file:
-                file.write(resp.content)
+            if output_file:
+                with open(output_file, "wb") as file:
+                    file.write(resp.content)
+            else:
+                return resp.content
         else:
             error_msg = f"Custom TTS请求失败: {resp.status_code} - {resp.text}"
             logger.bind(tag=TAG).error(error_msg)

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

@@ -29,7 +29,7 @@ class TTSProvider(TTSProviderBase):
         speed_ratio = config.get("speed_ratio", "1.0")
         volume_ratio = config.get("volume_ratio", "1.0")
         pitch_ratio = config.get("pitch_ratio", "1.0")
-
+        self.audio_file_type = config.get("format", "wav")
         self.speed_ratio = float(speed_ratio) if speed_ratio else 1.0
         self.volume_ratio = float(volume_ratio) if volume_ratio else 1.0
         self.pitch_ratio = float(pitch_ratio) if pitch_ratio else 1.0
@@ -49,7 +49,7 @@ class TTSProvider(TTSProviderBase):
             "user": {"uid": "1"},
             "audio": {
                 "voice_type": self.voice,
-                "encoding": "wav",
+                "encoding": self.audio_file_type,
                 "speed_ratio": self.speed_ratio,
                 "volume_ratio": self.volume_ratio,
                 "pitch_ratio": self.pitch_ratio,
@@ -70,8 +70,12 @@ class TTSProvider(TTSProviderBase):
             )
             if "data" in resp.json():
                 data = resp.json()["data"]
-                file_to_save = open(output_file, "wb")
-                file_to_save.write(base64.b64decode(data))
+                audio_bytes = base64.b64decode(data)
+                if output_file:
+                    with open(output_file, "wb") as file_to_save:
+                        file_to_save.write(audio_bytes)
+                else:
+                    return audio_bytes
             else:
                 raise Exception(
                     f"{__name__} status_code: {resp.status_code} response: {resp.content}"

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

@@ -12,6 +12,7 @@ class TTSProvider(TTSProviderBase):
             self.voice = config.get("private_voice")
         else:
             self.voice = config.get("voice")
+        self.audio_file_type = config.get("format", "mp3")
 
     def generate_filename(self, extension=".mp3"):
         return os.path.join(
@@ -22,16 +23,24 @@ class TTSProvider(TTSProviderBase):
     async def text_to_speak(self, text, output_file):
         try:
             communicate = edge_tts.Communicate(text, voice=self.voice)
-            # 确保目录存在并创建空文件
-            os.makedirs(os.path.dirname(output_file), exist_ok=True)
-            with open(output_file, "wb") as f:
-                pass
+            if output_file:
+                # 确保目录存在并创建空文件
+                os.makedirs(os.path.dirname(output_file), exist_ok=True)
+                with open(output_file, "wb") as f:
+                    pass
 
-            # 流式写入音频数据
-            with open(output_file, "ab") as f:  # 改为追加模式避免覆盖
+                # 流式写入音频数据
+                with open(output_file, "ab") as f:  # 改为追加模式避免覆盖
+                    async for chunk in communicate.stream():
+                        if chunk["type"] == "audio":  # 只处理音频数据块
+                            f.write(chunk["data"])
+            else:
+                # 返回音频二进制数据
+                audio_bytes = b""
                 async for chunk in communicate.stream():
-                    if chunk["type"] == "audio":  # 只处理音频数据块
-                        f.write(chunk["data"])
+                    if chunk["type"] == "audio":
+                        audio_bytes += chunk["data"]
+                return audio_bytes
         except Exception as e:
             error_msg = f"Edge TTS请求失败: {e}"
             raise Exception(error_msg)  # 抛出异常，让调用方捕获

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

@@ -88,7 +88,7 @@ class TTSProvider(TTSProviderBase):
         self.reference_audio = parse_string_to_list(config.get("reference_audio"))
         self.reference_text = parse_string_to_list(config.get("reference_text"))
         self.format = config.get("response_format", "wav")
-
+        self.audio_file_type = config.get("response_format", "wav")
         self.api_key = config.get("api_key", "YOUR_API_KEY")
         have_key = check_model_key("FishSpeech TTS", self.api_key)
         if not have_key:
@@ -170,8 +170,11 @@ class TTSProvider(TTSProviderBase):
         if response.status_code == 200:
             audio_content = response.content
 
-            with open(output_file, "wb") as audio_file:
-                audio_file.write(audio_content)
+            if output_file:
+                with open(output_file, "wb") as audio_file:
+                    audio_file.write(audio_content)
+            else:
+                return audio_content
 
         else:
             error_msg = f"Request failed with status code {response.status_code}"

main/xiaozhi-server/core/providers/tts/gpt_sovits_v2.py

@@ -65,6 +65,7 @@ class TTSProvider(TTSProviderBase):
         self.aux_ref_audio_paths = parse_string_to_list(
             config.get("aux_ref_audio_paths")
         )
+        self.audio_file_type = config.get("format", "wav")
 
     async def text_to_speak(self, text, output_file):
         request_json = {
@@ -91,8 +92,11 @@ class TTSProvider(TTSProviderBase):
 
         resp = requests.post(self.url, json=request_json)
         if resp.status_code == 200:
-            with open(output_file, "wb") as file:
-                file.write(resp.content)
+            if output_file:
+                with open(output_file, "wb") as file:
+                    file.write(resp.content)
+            else:
+                return resp.content
         else:
             error_msg = f"GPT_SoVITS_V2 TTS请求失败: {resp.status_code} - {resp.text}"
             logger.bind(tag=TAG).error(error_msg)

main/xiaozhi-server/core/providers/tts/gpt_sovits_v3.py

@@ -32,6 +32,7 @@ class TTSProvider(TTSProviderBase):
         self.cut_punc = config.get("cut_punc", "")
         self.inp_refs = parse_string_to_list(config.get("inp_refs"))
         self.if_sr = str(config.get("if_sr", False)).lower() in ("true", "1", "yes")
+        self.audio_file_type = config.get("format", "wav")
 
     async def text_to_speak(self, text, output_file):
         request_params = {
@@ -52,8 +53,11 @@ class TTSProvider(TTSProviderBase):
 
         resp = requests.get(self.url, params=request_params)
         if resp.status_code == 200:
-            with open(output_file, "wb") as file:
-                file.write(resp.content)
+            if output_file:
+                with open(output_file, "wb") as file:
+                    file.write(resp.content)
+            else:
+                return resp.content
         else:
             error_msg = f"GPT_SoVITS_V3 TTS请求失败: {resp.status_code} - {resp.text}"
             logger.bind(tag=TAG).error(error_msg)

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

@@ -52,6 +52,7 @@ class TTSProvider(TTSProviderBase):
             "Content-Type": "application/json",
             "Authorization": f"Bearer {self.api_key}",
         }
+        self.audio_file_type = defult_audio_setting.get("format", "mp3")
 
     def generate_filename(self, extension=".mp3"):
         return os.path.join(
@@ -80,8 +81,12 @@ class TTSProvider(TTSProviderBase):
             # 检查返回请求数据的status_code是否为0
             if resp.json()["base_resp"]["status_code"] == 0:
                 data = resp.json()["data"]["audio"]
-                file_to_save = open(output_file, "wb")
-                file_to_save.write(bytes.fromhex(data))
+                audio_bytes = bytes.fromhex(data)
+                if output_file:
+                    with open(output_file, "wb") as file_to_save:
+                        file_to_save.write(audio_bytes)
+                else:
+                    return audio_bytes
             else:
                 raise Exception(
                     f"{__name__} status_code: {resp.status_code} response: {resp.content}"

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

@@ -17,7 +17,8 @@ class TTSProvider(TTSProviderBase):
             self.voice = config.get("private_voice")
         else:
             self.voice = config.get("voice", "alloy")
-        self.response_format = "wav"
+        self.response_format = config.get("format", "wav")
+        self.audio_file_type = config.get("format", "wav")
 
         # 处理空字符串的情况
         speed = config.get("speed", "1.0")
@@ -40,8 +41,11 @@ class TTSProvider(TTSProviderBase):
         }
         response = requests.post(self.api_url, json=data, headers=headers)
         if response.status_code == 200:
-            with open(output_file, "wb") as audio_file:
-                audio_file.write(response.content)
+            if output_file:
+                with open(output_file, "wb") as audio_file:
+                    audio_file.write(response.content)
+            else:
+                return response.content
         else:
             raise Exception(
                 f"OpenAI TTS请求失败: {response.status_code} - {response.text}"

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

@@ -11,7 +11,8 @@ class TTSProvider(TTSProviderBase):
             self.voice = config.get("private_voice")
         else:
             self.voice = config.get("voice")
-        self.response_format = config.get("response_format")
+        self.response_format = config.get("response_format", "mp3")
+        self.audio_file_type = config.get("response_format", "mp3")
         self.sample_rate = config.get("sample_rate")
         self.speed = float(config.get("speed", 1.0))
         self.gain = config.get("gain")
@@ -35,7 +36,10 @@ class TTSProvider(TTSProviderBase):
                 "POST", self.api_url, json=request_json, headers=headers
             )
             data = response.content
-            file_to_save = open(output_file, "wb")
-            file_to_save.write(data)
+            if output_file:
+                with open(output_file, "wb") as file_to_save:
+                    file_to_save.write(data)
+            else:
+                return data
         except Exception as e:
             raise Exception(f"{__name__} error: {e}")

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

@@ -22,6 +22,7 @@ class TTSProvider(TTSProviderBase):
         self.api_url = "https://tts.tencentcloudapi.com"  # 正确的API端点
         self.region = config.get("region")
         self.output_file = config.get("output_dir")
+        self.audio_file_type = config.get("format", "wav")
 
     def _get_auth_headers(self, request_body):
         """生成鉴权请求头"""
@@ -148,12 +149,14 @@ class TTSProvider(TTSProviderBase):
                         f"API返回错误: {error_info['Code']}: {error_info['Message']}"
                     )
 
-                # 提取音频数据
-                audio_data = response_data["Response"].get("Audio")
-                if audio_data:
-                    # 解码Base64音频数据并保存
-                    with open(output_file, "wb") as f:
-                        f.write(base64.b64decode(audio_data))
+                # 解码Base64音频数据
+                audio_bytes = base64.b64decode(response_data["Response"].get("Audio"))
+                if audio_bytes:
+                    if output_file:
+                        with open(output_file, "wb") as f:
+                            f.write(audio_bytes)
+                    else:
+                        return audio_bytes
                 else:
                     raise Exception(f"{__name__}: 没有返回音频数据: {response_data}")
             else:

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

@@ -30,6 +30,7 @@ class TTSProvider(TTSProviderBase):
         self.output_file = config.get("output_dir")
         self.pitch_factor = int(config.get("pitch_factor", 0))
         self.format = config.get("format", "mp3")
+        self.audio_file_type = config.get("format", "mp3")
         self.emotion = int(config.get("emotion", 1))
         self.header = {"Content-Type": "application/json"}
 
@@ -73,9 +74,11 @@ class TTSProvider(TTSProviderBase):
             )
 
             audio_content = requests.get(result)
-            with open(output_file, "wb") as f:
-                f.write(audio_content.content)
-                return True
+            if output_file:
+                with open(output_file, "wb") as f:
+                    f.write(audio_content.content)
+            else:
+                return audio_content.content
             voice_path = resp_json.get("voice_path")
             des_path = output_file
             shutil.move(voice_path, des_path)