mirror of
https://github.com/xinnan-tech/xiaozhi-esp32-server.git
synced 2026-07-22 23:23:55 +08:00
0e43748fdc
* 🦄 refactor(web): 修改zhikongtaiweb到web * 🦄 refactor: 重写前端 路由守护尚未写完 * 🦄 refactor: 标准化路由 * update:前端重写，保留后端 * update:添加前端代码 * update:pip转成poetry启动 * update:增加mem0ai包依赖 * update:文档增加mem0ai的描述 * feat: play online mp3 (#181) Co-authored-by: 欣南科技 <huangrongzhuang@xin-nan.com> * 修改前端代码 * update:调整项目目录 * update:优化 * update:配置文件去除8002端口 * update:增加开发说明 * update:更新开发协议 --------- Co-authored-by: kalicyh <34980061+kaliCYH@users.noreply.github.com> Co-authored-by: hrz <1710360675@qq.com> Co-authored-by: freshlife001 <talent@mises.site> Co-authored-by: CGD <3030332422@qq.com>
84 lines
2.5 KiB
Python
84 lines
2.5 KiB
Python
from config.logger import setup_logging
|
|
import json
|
|
import asyncio
|
|
import time
|
|
from core.utils.util import remove_punctuation_and_length, get_string_no_punctuation_or_emoji
|
|
|
|
TAG = __name__
|
|
logger = setup_logging()
|
|
|
|
|
|
async def isLLMWantToFinish(last_text):
|
|
_, last_text_without_punctuation = remove_punctuation_and_length(last_text)
|
|
if "再见" in last_text_without_punctuation or "拜拜" in last_text_without_punctuation:
|
|
return True
|
|
return False
|
|
|
|
|
|
async def sendAudioMessage(conn, audios, text, text_index=0):
|
|
# 发送句子开始消息
|
|
if text_index == conn.tts_first_text_index:
|
|
logger.bind(tag=TAG).info(f"发送第一段语音: {text}")
|
|
await send_tts_message(conn, "sentence_start", text)
|
|
|
|
# 初始化流控参数
|
|
frame_duration = 60 # 毫秒
|
|
start_time = time.perf_counter() # 使用高精度计时器
|
|
play_position = 0 # 已播放的时长（毫秒）
|
|
|
|
for opus_packet in audios:
|
|
if conn.client_abort:
|
|
return
|
|
|
|
# 计算当前包的预期发送时间
|
|
expected_time = start_time + (play_position / 1000)
|
|
current_time = time.perf_counter()
|
|
|
|
# 等待直到预期时间
|
|
delay = expected_time - current_time
|
|
if delay > 0:
|
|
await asyncio.sleep(delay)
|
|
|
|
# 发送音频包
|
|
await conn.websocket.send(opus_packet)
|
|
play_position += frame_duration # 更新播放位置
|
|
await send_tts_message(conn, "sentence_end", text)
|
|
# 发送结束消息（如果是最后一个文本）
|
|
if conn.llm_finish_task and text_index == conn.tts_last_text_index:
|
|
await send_tts_message(conn, 'stop', None)
|
|
if await isLLMWantToFinish(text):
|
|
await conn.close()
|
|
|
|
|
|
async def send_tts_message(conn, state, text=None):
|
|
"""发送 TTS 状态消息"""
|
|
message = {
|
|
"type": "tts",
|
|
"state": state,
|
|
"session_id": conn.session_id
|
|
}
|
|
if text is not None:
|
|
message["text"] = text
|
|
|
|
await conn.websocket.send(json.dumps(message))
|
|
if state == "stop":
|
|
conn.clearSpeakStatus()
|
|
|
|
|
|
async def send_stt_message(conn, text):
|
|
"""发送 STT 状态消息"""
|
|
stt_text = get_string_no_punctuation_or_emoji(text)
|
|
await conn.websocket.send(json.dumps({
|
|
"type": "stt",
|
|
"text": stt_text,
|
|
"session_id": conn.session_id}
|
|
))
|
|
await conn.websocket.send(
|
|
json.dumps({
|
|
"type": "llm",
|
|
"text": "😊",
|
|
"emotion": "happy",
|
|
"session_id": conn.session_id}
|
|
))
|
|
await send_tts_message(conn, "start")
|