Hass/xiaozhi-esp32-server
1
0
Fork 0
mirror of https://github.com/xinnan-tech/xiaozhi-esp32-server.git synced 2026-07-22 07:03:53 +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/manager-api/src/main/resources/db/changelog/202504131543.sql
+18
View File
@@ -0,0 +1,18 @@
-- 对0.3.0版本之前的参数进行修改
update `sys_params` set param_value = '.mp3;.wav;.p3' where param_code = 'plugins.play_music.music_ext';
update `ai_model_config` set config_json = '{\"type\": \"intent_llm\", \"llm\": \"LLM_ChatGLMLLM\"}' where id = 'Intent_intent_llm';
-- 添加edge音色
delete from `ai_tts_voice` where tts_model_id = 'TTS_EdgeTTS';
INSERT INTO `ai_tts_voice` VALUES
('TTS_EdgeTTS0001', 'TTS_EdgeTTS', 'EdgeTTS女声-晓晓', 'zh-CN-XiaoxiaoNeural', '普通话', NULL, NULL, 1, NULL, NULL, NULL, NULL),
('TTS_EdgeTTS0002', 'TTS_EdgeTTS', 'EdgeTTS男声-云扬', 'zh-CN-YunyangNeural', '普通话', NULL, NULL, 1, NULL, NULL, NULL, NULL),
('TTS_EdgeTTS0003', 'TTS_EdgeTTS', 'EdgeTTS女声-晓伊', 'zh-CN-XiaoyiNeural', '普通话', NULL, NULL, 1, NULL, NULL, NULL, NULL),
('TTS_EdgeTTS0004', 'TTS_EdgeTTS', 'EdgeTTS男声-云健', 'zh-CN-YunjianNeural', '普通话', NULL, NULL, 1, NULL, NULL, NULL, NULL),
('TTS_EdgeTTS0005', 'TTS_EdgeTTS', 'EdgeTTS男声-云希', 'zh-CN-YunxiNeural', '普通话', NULL, NULL, 1, NULL, NULL, NULL, NULL),
('TTS_EdgeTTS0006', 'TTS_EdgeTTS', 'EdgeTTS男声-云夏', 'zh-CN-YunxiaNeural', '普通话', NULL, NULL, 1, NULL, NULL, NULL, NULL),
('TTS_EdgeTTS0007', 'TTS_EdgeTTS', 'EdgeTTS女声-辽宁小贝', 'zh-CN-liaoning-XiaobeiNeural', '辽宁', NULL, NULL, 1, NULL, NULL, NULL, NULL),
('TTS_EdgeTTS0008', 'TTS_EdgeTTS', 'EdgeTTS女声-陕西小妮', 'zh-CN-shaanxi-XiaoniNeural', '陕西', NULL, NULL, 1, NULL, NULL, NULL, NULL),
('TTS_EdgeTTS0009', 'TTS_EdgeTTS', 'EdgeTTS女声-香港海佳', 'zh-HK-HiuGaaiNeural', '粤语', 'General', 'Friendly, Positive', 1, NULL, NULL, NULL, NULL),
('TTS_EdgeTTS0010', 'TTS_EdgeTTS', 'EdgeTTS女声-香港海曼', 'zh-HK-HiuMaanNeural', '粤语', 'General', 'Friendly, Positive', 1, NULL, NULL, NULL, NULL),
('TTS_EdgeTTS0011', 'TTS_EdgeTTS', 'EdgeTTS男声-香港万龙', 'zh-HK-WanLungNeural', '粤语', 'General', 'Friendly, Positive', 1, NULL, NULL, NULL, NULL);
main/manager-api/src/main/resources/db/changelog/db.changelog-master.yaml
+2 -2
View File
@@ -52,9 +52,9 @@ databaseChangeLog:
encoding: utf8
path: classpath:db/changelog/202504112058.sql
- changeSet:
id: 202504131542
id: 202504131543
author: John
changes:
- sqlFile:
encoding: utf8
path: classpath:db/changelog/202504131542.sql
path: classpath:db/changelog/202504131543.sql
main/xiaozhi-server/core/providers/tts/cozecn.py
+12 -4
View File
@@ -12,14 +12,20 @@ class TTSProvider(TTSProviderBase):
super().__init__(config, delete_audio_file)
self.model = config.get("model")
self.access_token = config.get("access_token")
self.voice = config.get("voice")
if config.get("private_voice"):
self.voice = config.get("private_voice")
else:
self.voice = config.get("voice")
self.response_format = config.get("response_format")
self.host = "api.coze.cn"
self.api_url = f"https://{self.host}/v1/audio/speech"
def generate_filename(self, extension=".wav"):
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):
request_json = {
@@ -30,9 +36,11 @@ class TTSProvider(TTSProviderBase):
}
headers = {
"Authorization": f"Bearer {self.access_token}",
"Content-Type": "application/json"
"Content-Type": "application/json",
}
response = requests.request("POST", self.api_url, json=request_json, headers=headers)
response = requests.request(
"POST", self.api_url, json=request_json, headers=headers
)
data = response.content
file_to_save = open(output_file, "wb")
file_to_save.write(data)
main/xiaozhi-server/core/providers/tts/doubao.py
+6 -1
View File
@@ -18,7 +18,12 @@ class TTSProvider(TTSProviderBase):
self.appid = config.get("appid")
self.access_token = config.get("access_token")
self.cluster = config.get("cluster")
self.voice = config.get("voice")
if config.get("private_voice"):
self.voice = config.get("private_voice")
else:
self.voice = config.get("voice")
self.api_url = config.get("api_url")
self.authorization = config.get("authorization")
self.header = {"Authorization": f"{self.authorization}{self.access_token}"}
main/xiaozhi-server/core/providers/tts/edge.py
+11 -5
View File
@@ -8,20 +8,26 @@ from core.providers.tts.base import TTSProviderBase
class TTSProvider(TTSProviderBase):
def __init__(self, config, delete_audio_file):
super().__init__(config, delete_audio_file)
self.voice = config.get("voice")
if config.get("private_voice"):
self.voice = config.get("private_voice")
else:
self.voice = config.get("voice")
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):
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:
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
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"])
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}")
main/xiaozhi-server/core/providers/tts/openai.py
+4 -1
View File
@@ -16,7 +16,10 @@ class TTSProvider(TTSProviderBase):
self.api_key = config.get("api_key")
self.api_url = config.get("api_url", "https://api.openai.com/v1/audio/speech")
self.model = config.get("model", "tts-1")
self.voice = config.get("voice", "alloy")
if config.get("private_voice"):
self.voice = config.get("private_voice")
else:
self.voice = config.get("voice", "alloy")
self.response_format = "wav"
self.speed = config.get("speed", 1.0)
self.output_file = config.get("output_dir", "tmp/")
main/xiaozhi-server/core/providers/tts/siliconflow.py
+12 -4
View File
@@ -10,7 +10,10 @@ class TTSProvider(TTSProviderBase):
super().__init__(config, delete_audio_file)
self.model = config.get("model")
self.access_token = config.get("access_token")
self.voice = config.get("voice")
if config.get("private_voice"):
self.voice = config.get("private_voice")
else:
self.voice = config.get("voice")
self.response_format = config.get("response_format")
self.sample_rate = config.get("sample_rate")
self.speed = config.get("speed")
@@ -20,7 +23,10 @@ class TTSProvider(TTSProviderBase):
self.api_url = f"https://{self.host}/v1/audio/speech"
def generate_filename(self, extension=".wav"):
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):
request_json = {
@@ -31,9 +37,11 @@ class TTSProvider(TTSProviderBase):
}
headers = {
"Authorization": f"Bearer {self.access_token}",
"Content-Type": "application/json"
"Content-Type": "application/json",
}
response = requests.request("POST", self.api_url, json=request_json, headers=headers)
response = requests.request(
"POST", self.api_url, json=request_json, headers=headers
)
data = response.content
file_to_save = open(output_file, "wb")
file_to_save.write(data)
main/xiaozhi-server/core/providers/tts/tencent.py
+52 -37
View File
@@ -16,7 +16,10 @@ class TTSProvider(TTSProviderBase):
self.appid = config.get("appid")
self.secret_id = config.get("secret_id")
self.secret_key = config.get("secret_key")
self.voice = config.get("voice")
if config.get("private_voice"):
self.voice = config.get("private_voice")
else:
self.voice = config.get("voice")
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")
@@ -25,35 +28,36 @@ class TTSProvider(TTSProviderBase):
"""生成鉴权请求头"""
# 获取当前UTC时间戳
timestamp = int(time.time())
# 使用UTC时间计算日期
utc_date = datetime.fromtimestamp(timestamp, tz=timezone.utc).strftime('%Y-%m-%d')
utc_date = datetime.fromtimestamp(timestamp, tz=timezone.utc).strftime(
"%Y-%m-%d"
)
# 服务名称必须是 "tts"
service = "tts"
# 拼接凭证范围
credential_scope = f"{utc_date}/{service}/tc3_request"
# 使用TC3-HMAC-SHA256签名方法
algorithm = "TC3-HMAC-SHA256"
# 构建规范请求字符串
http_request_method = "POST"
canonical_uri = "/"
canonical_querystring = ""
# 请求头必须包含host和content-type，且按字典序排列
canonical_headers = (
f"content-type:application/json\n"
f"host:tts.tencentcloudapi.com\n"
f"content-type:application/json\n" f"host:tts.tencentcloudapi.com\n"
)
signed_headers = "content-type;host"
# 请求体哈希值
payload = json.dumps(request_body)
payload_hash = hashlib.sha256(payload.encode('utf-8')).hexdigest()
payload_hash = hashlib.sha256(payload.encode("utf-8")).hexdigest()
# 构建规范请求字符串
canonical_request = (
f"{http_request_method}\n"
@@ -63,10 +67,12 @@ class TTSProvider(TTSProviderBase):
f"{signed_headers}\n"
f"{payload_hash}"
)
# 计算规范请求的哈希值
hashed_canonical_request = hashlib.sha256(canonical_request.encode('utf-8')).hexdigest()
hashed_canonical_request = hashlib.sha256(
canonical_request.encode("utf-8")
).hexdigest()
# 构建待签名字符串
string_to_sign = (
f"{algorithm}\n"
@@ -74,19 +80,19 @@ class TTSProvider(TTSProviderBase):
f"{credential_scope}\n"
f"{hashed_canonical_request}"
)
# 计算签名密钥
secret_date = self._hmac_sha256(f"TC3{self.secret_key}".encode('utf-8'), utc_date)
secret_date = self._hmac_sha256(
f"TC3{self.secret_key}".encode("utf-8"), utc_date
)
secret_service = self._hmac_sha256(secret_date, service)
secret_signing = self._hmac_sha256(secret_service, "tc3_request")
# 计算签名
signature = hmac.new(
secret_signing,
string_to_sign.encode('utf-8'),
hashlib.sha256
secret_signing, string_to_sign.encode("utf-8"), hashlib.sha256
).hexdigest()
# 构建授权头
authorization = (
f"{algorithm} "
@@ -94,7 +100,7 @@ class TTSProvider(TTSProviderBase):
f"SignedHeaders={signed_headers}, "
f"Signature={signature}"
)
# 构建请求头
headers = {
"Content-Type": "application/json",
@@ -104,19 +110,22 @@ class TTSProvider(TTSProviderBase):
"X-TC-Timestamp": str(timestamp),
"X-TC-Version": "2019-08-23",
"X-TC-Region": self.region,
"X-TC-Language": "zh-CN"
"X-TC-Language": "zh-CN",
}
return headers
def _hmac_sha256(self, key, msg):
"""HMAC-SHA256加密"""
if isinstance(msg, str):
msg = msg.encode('utf-8')
msg = msg.encode("utf-8")
return hmac.new(key, msg, hashlib.sha256).digest()
def generate_filename(self, extension=".wav"):
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):
# 构建请求体
@@ -129,19 +138,23 @@ class TTSProvider(TTSProviderBase):
try:
# 获取请求头（每次请求都重新生成，以确保时间戳和签名是最新的）
headers = self._get_auth_headers(request_json)
# 发送请求
resp = requests.post(self.api_url, json.dumps(request_json), headers=headers)
resp = requests.post(
self.api_url, json.dumps(request_json), headers=headers
)
# 检查响应
if resp.status_code == 200:
response_data = resp.json()
# 检查是否成功
if response_data.get("Response", {}).get("Error") is not None:
error_info = response_data["Response"]["Error"]
raise Exception(f"API返回错误: {error_info['Code']}: {error_info['Message']}")
raise Exception(
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:
@@ -151,6 +164,8 @@ class TTSProvider(TTSProviderBase):
else:
raise Exception(f"{__name__}: 没有返回音频数据: {response_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}")
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)