Hass/xiaozhi-esp32-server
1
0
Fork 0
mirror of https://github.com/xinnan-tech/xiaozhi-esp32-server.git synced 2026-07-31 03:43:57 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix:智能体音色未随manager生效bug

Browse Source 
* fix:连接manager后无法使用functioncallbug

* fix:意图识别使用llm无法播放音乐bug

* fix：manager第一图识别使用独立llm无法初始化llm的bug

* fix:智能体音色未随manager生效bug

* update:添加edgeTTS音色
This commit is contained in:
hrz
2025-04-13 19:01:19 +08:00
committed by GitHub
parent de8c762d79
commit 4912f385c6
10 changed files with 181 additions and 92 deletions
Download Patch File Download Diff File Expand all files Collapse all files
main/xiaozhi-server/core/providers/tts/minimax.py
+28 -16
View File
@@ -12,28 +12,33 @@ class TTSProvider(TTSProviderBase):
self.group_id = config.get("group_id")
self.api_key = config.get("api_key")
self.model = config.get("model")
self.voice_id = config.get("voice_id")
if config.get("private_voice"):
self.voice_id = config.get("private_voice")
else:
self.voice_id = config.get("voice_id")
default_voice_setting = {
"voice_id": "female-shaonv",
"speed": 1,
"vol": 1,
"pitch": 0,
"emotion": "happy"
}
default_pronunciation_dict = {
"tone": [
"处理/(chu3)(li3)", "危险/dangerous"
]
"emotion": "happy",
}
default_pronunciation_dict = {"tone": ["处理/(chu3)(li3)", "危险/dangerous"]}
defult_audio_setting = {
"sample_rate": 32000,
"bitrate": 128000,
"format": "mp3",
"channel": 1
"channel": 1,
}
self.voice_setting = {
**default_voice_setting,
**config.get("voice_setting", {}),
}
self.pronunciation_dict = {
**default_pronunciation_dict,
**config.get("pronunciation_dict", {}),
}
self.voice_setting = {**default_voice_setting, **config.get("voice_setting", {})}
self.pronunciation_dict = {**default_pronunciation_dict, **config.get("pronunciation_dict", {})}
self.audio_setting = {**defult_audio_setting, **config.get("audio_setting", {})}
self.timber_weights = config.get("timber_weights", [])
@@ -44,11 +49,14 @@ class TTSProvider(TTSProviderBase):
self.api_url = f"https://{self.host}/v1/t2a_v2?GroupId={self.group_id}"
self.header = {
"Content-Type": "application/json",
"Authorization": f"Bearer {self.api_key}"
"Authorization": f"Bearer {self.api_key}",
}
def generate_filename(self, extension=".mp3"):
return os.path.join(self.output_file, f"tts-{__name__}{datetime.now().date()}@{uuid.uuid4().hex}{extension}")
return os.path.join(
self.output_file,
f"tts-{__name__}{datetime.now().date()}@{uuid.uuid4().hex}{extension}",
)
async def text_to_speak(self, text, output_file):
request_json = {
@@ -65,13 +73,17 @@ class TTSProvider(TTSProviderBase):
request_json["voice_setting"]["voice_id"] = ""
try:
resp = requests.post(self.api_url, json.dumps(request_json), headers=self.header)
resp = requests.post(
self.api_url, json.dumps(request_json), headers=self.header
)
# 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']
data = resp.json()["data"]["audio"]
file_to_save = open(output_file, "wb")
file_to_save.write(bytes.fromhex(data))
else:
raise Exception(f"{__name__} status_code: {resp.status_code} response: {resp.content}")
raise Exception(
f"{__name__} status_code: {resp.status_code} response: {resp.content}"
)
except Exception as e:
raise Exception(f"{__name__} error: {e}")
raise Exception(f"{__name__} error: {e}")