Hass/xiaozhi-esp32-server
1
0
Fork 0
mirror of https://github.com/xinnan-tech/xiaozhi-esp32-server.git synced 2026-07-31 01:33:57 +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/ttson.py
+36 -22
View File
@@ -10,8 +10,14 @@ from core.providers.tts.base import TTSProviderBase
class TTSProvider(TTSProviderBase):
def __init__(self, config, delete_audio_file):
super().__init__(config, delete_audio_file)
self.url = config.get("url", "https://u95167-bd74-2aef8085.westx.seetacloud.com:8443/flashsummary/tts?token=")
self.voice_id = config.get("voice_id", 1695)
self.url = config.get(
"url",
"https://u95167-bd74-2aef8085.westx.seetacloud.com:8443/flashsummary/tts?token=",
)
if config.get("private_voice"):
self.voice_id = int(config.get("private_voice"))
else:
self.voice_id = int(config.get("voice_id", 1695))
self.token = config.get("token")
self.to_lang = config.get("to_lang")
self.volume_change_dB = config.get("volume_change_dB", 0)
@@ -21,37 +27,45 @@ class TTSProvider(TTSProviderBase):
self.pitch_factor = config.get("pitch_factor", 0)
self.format = config.get("format", "mp3")
self.emotion = config.get("emotion", 1)
self.header = {
"Content-Type": "application/json"
}
self.header = {"Content-Type": "application/json"}
def generate_filename(self, extension=".mp3"):
return os.path.join(self.output_file, f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}")
return os.path.join(
self.output_file,
f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}",
)
async def text_to_speak(self, text, output_file):
url = f'{self.url}{self.token}'
url = f"{self.url}{self.token}"
result = "firefly"
payload = json.dumps({
"to_lang": self.to_lang,
"text": text,
"emotion": self.emotion,
"format": self.format,
"volume_change_dB": self.volume_change_dB,
"voice_id": self.voice_id,
"pitch_factor": self.pitch_factor,
"speed_factor": self.speed_factor,
"token": self.token
})
payload = json.dumps(
{
"to_lang": self.to_lang,
"text": text,
"emotion": self.emotion,
"format": self.format,
"volume_change_dB": self.volume_change_dB,
"voice_id": self.voice_id,
"pitch_factor": self.pitch_factor,
"speed_factor": self.speed_factor,
"token": self.token,
}
)
resp = requests.request("POST", url, data=payload)
if resp.status_code != 200:
return None
resp_json = resp.json()
try:
result = resp_json['url'] + ':' + str(
resp_json[
'port']) + '/flashsummary/retrieveFileData?stream=True&token=' + self.token + '&voice_audio_path=' + \
resp_json['voice_path']
result = (
resp_json["url"]
+ ":"
+ str(resp_json["port"])
+ "/flashsummary/retrieveFileData?stream=True&token="
+ self.token
+ "&voice_audio_path="
+ resp_json["voice_path"]
)
except Exception as e:
print("error:", e)