Hass/xiaozhi-esp32-server
1
0
Fork 0
mirror of https://github.com/xinnan-tech/xiaozhi-esp32-server.git synced 2026-07-30 05:13:59 +08:00
Code Issues Packages Projects Releases Wiki Activity

update:server连接api (#747)

Browse Source 
* update:server连接manager-api

* update:读取智能体模型配置

* update:添加默认模型的按钮

* update:优化配置读取方式

* update：server兼容manager接口改造

* update:优化私有配置加载

* update:加载私有模型配置
This commit is contained in:
hrz
2025-04-12 17:36:04 +08:00
committed by GitHub
parent c39ad97b8e
commit 5d69ba0796
57 changed files with 1618 additions and 1066 deletions
Download Patch File Download Diff File Expand all files Collapse all files
main/xiaozhi-server/core/providers/tts/doubao.py
+18 -9
View File
@@ -6,6 +6,10 @@ import requests
from datetime import datetime
from core.utils.util import check_model_key
from core.providers.tts.base import TTSProviderBase
from config.logger import setup_logging
TAG = __name__
logger = setup_logging()
class TTSProvider(TTSProviderBase):
@@ -21,18 +25,19 @@ class TTSProvider(TTSProviderBase):
check_model_key("TTS", self.access_token)
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 = {
"app": {
"appid": f"{self.appid}",
"token": "access_token",
"cluster": self.cluster
},
"user": {
"uid": "1"
"cluster": self.cluster,
},
"user": {"uid": "1"},
"audio": {
"voice_type": self.voice,
"encoding": "wav",
@@ -46,17 +51,21 @@ class TTSProvider(TTSProviderBase):
"text_type": "plain",
"operation": "query",
"with_frontend": 1,
"frontend_type": "unitTson"
}
"frontend_type": "unitTson",
},
}
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
)
if "data" in resp.json():
data = resp.json()["data"]
file_to_save = open(output_file, "wb")
file_to_save.write(base64.b64decode(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}")
main/xiaozhi-server/core/providers/tts/fishspeech.py
+9 -8
View File
@@ -24,7 +24,7 @@ class ServeReferenceAudio(BaseModel):
def decode_audio(cls, values):
audio = values.get("audio")
if (
isinstance(audio, str) and len(audio) > 255
isinstance(audio, str) and len(audio) > 255
): # Check if audio is a string (Base64)
try:
values["audio"] = base64.b64decode(audio)
@@ -107,7 +107,10 @@ class TTSProvider(TTSProviderBase):
self.api_url = config.get("api_url", "http://127.0.0.1:8080/v1/tts")
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):
# Prepare reference data
@@ -117,9 +120,7 @@ class TTSProvider(TTSProviderBase):
data = {
"text": text,
"references": [
ServeReferenceAudio(
audio=audio if audio else b"", text=text
)
ServeReferenceAudio(audio=audio if audio else b"", text=text)
for text, audio in zip(ref_texts, byte_audios)
],
"reference_id": self.reference_id,
@@ -139,7 +140,9 @@ class TTSProvider(TTSProviderBase):
response = requests.post(
self.api_url,
data=ormsgpack.packb(pydantic_data, option=ormsgpack.OPT_SERIALIZE_PYDANTIC),
data=ormsgpack.packb(
pydantic_data, option=ormsgpack.OPT_SERIALIZE_PYDANTIC
),
headers={
"Authorization": f"Bearer {self.api_key}",
"Content-Type": "application/msgpack",
@@ -152,8 +155,6 @@ class TTSProvider(TTSProviderBase):
with open(output_file, "wb") as audio_file:
audio_file.write(audio_content)
else:
print(f"Request failed with status code {response.status_code}")
print(response.json())
main/xiaozhi-server/core/providers/tts/openai.py
+14 -4
View File
@@ -4,6 +4,11 @@ import requests
from datetime import datetime
from core.utils.util import check_model_key
from core.providers.tts.base import TTSProviderBase
from config.logger import setup_logging
TAG = __name__
logger = setup_logging()
class TTSProvider(TTSProviderBase):
def __init__(self, config, delete_audio_file):
@@ -18,23 +23,28 @@ class TTSProvider(TTSProviderBase):
check_model_key("TTS", self.api_key)
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):
headers = {
"Authorization": f"Bearer {self.api_key}",
"Content-Type": "application/json"
"Content-Type": "application/json",
}
data = {
"model": self.model,
"input": text,
"voice": self.voice,
"response_format": "wav",
"speed": self.speed
"speed": self.speed,
}
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)
else:
raise Exception(f"OpenAI TTS请求失败: {response.status_code} - {response.text}")
raise Exception(
f"OpenAI TTS请求失败: {response.status_code} - {response.text}"
)