mirror of
https://github.com/xinnan-tech/xiaozhi-esp32-server.git
synced 2026-07-28 10:03:54 +08:00
Merge old pr (#235)
* 新增openai tts (#137) On branch openai_tts Changes to be committed: modified: config.yaml new file: core/providers/tts/openai_tts.py Co-authored-by: 欣南科技 <huangrongzhuang@xin-nan.com> * Update config.yaml (#201) * 修改了coze的实现方式,使用了v3接口,修复了只能对话一次的bug * 使用mem0ai api实现记忆功能 * Fix docker space (#179) * update:调试docker编译缓存 * update:调试docker编译 * update:调试docker编译容量 * update:调试docker编译 --------- Co-authored-by: hrz <1710360675@qq.com> * TTS处理增加index信息，完善TTS出错时的处理 (#177) * TTS处理增加index信息，完善TTS出错时的处理 * 第一句语音index处理，歌曲播放index处理 * update:去掉了无用变量，修复continuebug --------- Co-authored-by: hrz <1710360675@qq.com> * update:更新demo (#180) Co-authored-by: hrz <1710360675@qq.com> * 优化chat中异步调用方式 * 记忆增加时间，以便大模型判断先后关系 * 记忆对时间戳排序，便于梳理前后关系 * add: 不跟踪music下的文件的更改 (#187) * Mem0ai (#199) * update:增加mem0ai包依赖 * update:文档增加mem0ai的描述 --------- Co-authored-by: hrz <1710360675@qq.com> * Update config.yaml * Update config.yaml * Update config.yaml * Update config.yaml --------- Co-authored-by: strix214 <a1425699467@gmail.com> Co-authored-by: 玄凤科技 <eric230308@gmail.com> Co-authored-by: HonestQiao <honestqiao@163.com> Co-authored-by: 欣南科技 <huangrongzhuang@xin-nan.com> Co-authored-by: hrz <1710360675@qq.com> Co-authored-by: TOM88812 <ttangxs0808@163.com> Co-authored-by: 香草味的纳西妲 <151599587+NyaOH-Nahida@users.noreply.github.com> * update:添加忽略文件 * feat: 增加fastgpt适配：支持think、variables参数 (#213) * 修改了coze的实现方式,使用了v3接口,修复了只能对话一次的bug * 使用mem0ai api实现记忆功能 * Fix docker space (#179) * update:调试docker编译缓存 * update:调试docker编译 * update:调试docker编译容量 * update:调试docker编译 --------- Co-authored-by: hrz <1710360675@qq.com> * TTS处理增加index信息，完善TTS出错时的处理 (#177) * TTS处理增加index信息，完善TTS出错时的处理 * 第一句语音index处理，歌曲播放index处理 * update:去掉了无用变量，修复continuebug --------- Co-authored-by: hrz <1710360675@qq.com> * update:更新demo (#180) Co-authored-by: hrz <1710360675@qq.com> * 优化chat中异步调用方式 * 记忆增加时间，以便大模型判断先后关系 * 记忆对时间戳排序，便于梳理前后关系 * add: 不跟踪music下的文件的更改 (#187) * Mem0ai (#199) * update:增加mem0ai包依赖 * update:文档增加mem0ai的描述 --------- Co-authored-by: hrz <1710360675@qq.com> * feat: 增加fastgpt适配：支持think、variables参数 --------- Co-authored-by: strix214 <a1425699467@gmail.com> Co-authored-by: 玄凤科技 <eric230308@gmail.com> Co-authored-by: HonestQiao <honestqiao@163.com> Co-authored-by: 欣南科技 <huangrongzhuang@xin-nan.com> Co-authored-by: hrz <1710360675@qq.com> Co-authored-by: TOM88812 <ttangxs0808@163.com> Co-authored-by: 香草味的纳西妲 <151599587+NyaOH-Nahida@users.noreply.github.com> Co-authored-by: pt <ptsghs@163.com> * update：合并最新代码 * update:合并群友pr * update:openaitts 测试通过 * update:ACGNTTS测试完成 --------- Co-authored-by: Chris <119588753+Chris-websketch@users.noreply.github.com> Co-authored-by: ikun441 <3497689533@qq.com> Co-authored-by: strix214 <a1425699467@gmail.com> Co-authored-by: 玄凤科技 <eric230308@gmail.com> Co-authored-by: HonestQiao <honestqiao@163.com> Co-authored-by: hrz <1710360675@qq.com> Co-authored-by: TOM88812 <ttangxs0808@163.com> Co-authored-by: 香草味的纳西妲 <151599587+NyaOH-Nahida@users.noreply.github.com> Co-authored-by: ptisnoob <49125305+ptisnoob@users.noreply.github.com> Co-authored-by: pt <ptsghs@163.com>
This commit is contained in:
欣南科技
co-authored by
Chris
ikun441
strix214
玄凤科技
HonestQiao
hrz
TOM88812
香草味的纳西妲
ptisnoob
pt
Chris
ikun441
strix214
玄凤科技
HonestQiao
hrz
TOM88812
香草味的纳西妲
ptisnoob
pt
parent
6c52754c8f
commit
dd5fecdf5a
@@ -4,6 +4,7 @@ import json
|
||||
import base64
|
||||
import requests
|
||||
from datetime import datetime
|
||||
from core.utils.util import check_model_key
|
||||
from core.providers.tts.base import TTSProviderBase
|
||||
|
||||
|
||||
@@ -17,6 +18,7 @@ class TTSProvider(TTSProviderBase):
|
||||
self.api_url = config.get("api_url")
|
||||
self.authorization = config.get("authorization")
|
||||
self.header = {"Authorization": f"{self.authorization}{self.access_token}"}
|
||||
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}")
|
||||
|
||||
@@ -1,4 +1,3 @@
|
||||
|
||||
import base64
|
||||
import os
|
||||
import uuid
|
||||
@@ -9,6 +8,7 @@ from pydantic import BaseModel, Field, conint, model_validator
|
||||
from typing_extensions import Annotated
|
||||
from datetime import datetime
|
||||
from typing import Literal
|
||||
from core.utils.util import check_model_key
|
||||
from core.providers.tts.base import TTSProviderBase
|
||||
from config.logger import setup_logging
|
||||
|
||||
@@ -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)
|
||||
@@ -36,6 +36,7 @@ class ServeReferenceAudio(BaseModel):
|
||||
def __repr__(self) -> str:
|
||||
return f"ServeReferenceAudio(text={self.text!r}, audio_size={len(self.audio)})"
|
||||
|
||||
|
||||
class ServeTTSRequest(BaseModel):
|
||||
text: str
|
||||
chunk_length: Annotated[int, conint(ge=100, le=300, strict=True)] = 200
|
||||
@@ -70,6 +71,7 @@ def audio_to_bytes(file_path):
|
||||
wav = wav_file.read()
|
||||
return wav
|
||||
|
||||
|
||||
def read_ref_text(ref_text):
|
||||
path = Path(ref_text)
|
||||
if path.exists() and path.is_file():
|
||||
@@ -77,31 +79,32 @@ def read_ref_text(ref_text):
|
||||
return file.read()
|
||||
return ref_text
|
||||
|
||||
|
||||
class TTSProvider(TTSProviderBase):
|
||||
|
||||
def __init__(self, config, delete_audio_file):
|
||||
super().__init__(config, delete_audio_file)
|
||||
|
||||
self.reference_id = config.get("reference_id")
|
||||
self.reference_audio = config.get("reference_audio",[])
|
||||
self.reference_text = config.get("reference_text",[])
|
||||
self.format = config.get("format","wav")
|
||||
self.channels = config.get("channels",1)
|
||||
self.rate = config.get("rate",44100)
|
||||
self.api_key = config.get("api_key","YOUR_API_KEY")
|
||||
if "你" in self.api_key:
|
||||
logger.bind(tag=TAG).error("你还没配置FishSpeech TTS的密钥，请在配置文件中配置密钥，否则无法正常工作")
|
||||
self.reference_audio = config.get("reference_audio", [])
|
||||
self.reference_text = config.get("reference_text", [])
|
||||
self.format = config.get("format", "wav")
|
||||
self.channels = config.get("channels", 1)
|
||||
self.rate = config.get("rate", 44100)
|
||||
self.api_key = config.get("api_key", "YOUR_API_KEY")
|
||||
have_key = check_model_key("FishSpeech TTS", self.api_key)
|
||||
if not have_key:
|
||||
return
|
||||
self.normalize = config.get("normalize",True)
|
||||
self.max_new_tokens = config.get("max_new_tokens",1024)
|
||||
self.chunk_length = config.get("chunk_length",200)
|
||||
self.top_p = config.get("top_p",0.7)
|
||||
self.repetition_penalty = config.get("repetition_penalty",1.2)
|
||||
self.temperature = config.get("temperature",0.7)
|
||||
self.streaming = config.get("streaming",False)
|
||||
self.use_memory_cache = config.get("use_memory_cache","on")
|
||||
self.normalize = config.get("normalize", True)
|
||||
self.max_new_tokens = config.get("max_new_tokens", 1024)
|
||||
self.chunk_length = config.get("chunk_length", 200)
|
||||
self.top_p = config.get("top_p", 0.7)
|
||||
self.repetition_penalty = config.get("repetition_penalty", 1.2)
|
||||
self.temperature = config.get("temperature", 0.7)
|
||||
self.streaming = config.get("streaming", False)
|
||||
self.use_memory_cache = config.get("use_memory_cache", "on")
|
||||
self.seed = config.get("seed")
|
||||
self.api_url = config.get("api_url","http://127.0.0.1:8080/v1/tts")
|
||||
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}")
|
||||
@@ -148,11 +151,9 @@ 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())
|
||||
|
||||
|
||||
|
||||
@@ -0,0 +1,40 @@
|
||||
import os
|
||||
import uuid
|
||||
import requests
|
||||
from datetime import datetime
|
||||
from core.utils.util import check_model_key
|
||||
from core.providers.tts.base import TTSProviderBase
|
||||
|
||||
class TTSProvider(TTSProviderBase):
|
||||
def __init__(self, config, delete_audio_file):
|
||||
super().__init__(config, delete_audio_file)
|
||||
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")
|
||||
self.response_format = "wav"
|
||||
self.speed = config.get("speed", 1.0)
|
||||
self.output_file = config.get("output_file", "tmp/")
|
||||
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}")
|
||||
|
||||
async def text_to_speak(self, text, output_file):
|
||||
headers = {
|
||||
"Authorization": f"Bearer {self.api_key}",
|
||||
"Content-Type": "application/json"
|
||||
}
|
||||
data = {
|
||||
"model": self.model,
|
||||
"input": text,
|
||||
"voice": self.voice,
|
||||
"response_format": "wav",
|
||||
"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}")
|
||||
@@ -0,0 +1,64 @@
|
||||
import os
|
||||
import uuid
|
||||
import json
|
||||
import requests
|
||||
import shutil
|
||||
from datetime import datetime
|
||||
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.token = config.get("token")
|
||||
self.to_lang = config.get("to_lang")
|
||||
self.volume_change_dB = config.get("volume_change_dB", 0)
|
||||
self.speed_factor = config.get("speed_factor", 1)
|
||||
self.stream = config.get("stream", False)
|
||||
self.output_file = config.get("output_file")
|
||||
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"
|
||||
}
|
||||
|
||||
def generate_filename(self, extension=".mp3"):
|
||||
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}'
|
||||
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
|
||||
})
|
||||
|
||||
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']
|
||||
except Exception as e:
|
||||
print("error:", e)
|
||||
|
||||
audio_content = requests.get(result)
|
||||
with open(output_file, "wb") as f:
|
||||
f.write(audio_content.content)
|
||||
return True
|
||||
voice_path = resp_json.get("voice_path")
|
||||
des_path = output_file
|
||||
shutil.move(voice_path, des_path)
|
||||
Reference in New Issue
Block a user