mirror of
https://github.com/xinnan-tech/xiaozhi-esp32-server.git
synced 2026-07-26 09:03:54 +08:00
@@ -13,28 +13,37 @@ async def sendAudioMessage(conn, audios, text, text_index=0):
|
||||
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)
|
||||
# 流控参数优化
|
||||
original_frame_duration = 60 # 原始帧时长(毫秒)
|
||||
adjusted_frame_duration = int(original_frame_duration * 0.8) # 缩短20%
|
||||
total_frames = len(audios) # 获取总帧数
|
||||
compensation = total_frames * (original_frame_duration - adjusted_frame_duration) / 1000 # 补偿时间(秒)
|
||||
|
||||
start_time = time.perf_counter()
|
||||
play_position = 0 # 已播放时长(毫秒)
|
||||
|
||||
for opus_packet in audios:
|
||||
if conn.client_abort:
|
||||
return
|
||||
|
||||
# 计算当前包的预期发送时间
|
||||
# 计算带加速因子的预期时间
|
||||
expected_time = start_time + (play_position / 1000)
|
||||
current_time = time.perf_counter()
|
||||
|
||||
# 等待直到预期时间
|
||||
# 流控等待(使用加速后的帧时长)
|
||||
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
|
||||
play_position += adjusted_frame_duration # 使用调整后的帧时长
|
||||
|
||||
# 补偿因加速损失的时长
|
||||
if compensation > 0:
|
||||
await asyncio.sleep(compensation)
|
||||
|
||||
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)
|
||||
|
||||
Reference in New Issue
Block a user