From f45bc5d9c93ed58935ef70bb666221306b6f9b6b Mon Sep 17 00:00:00 2001 From: Sakura-RanChen <1908198662@qq.com> Date: Tue, 2 Sep 2025 15:24:51 +0800 Subject: [PATCH] =?UTF-8?q?=E4=BC=98=E5=8C=96=E9=9F=B3=E9=A2=91?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .../core/handle/receiveAudioHandle.py | 17 +++++++++++------ main/xiaozhi-server/core/utils/util.py | 19 ------------------- 2 files changed, 11 insertions(+), 25 deletions(-) diff --git a/main/xiaozhi-server/core/handle/receiveAudioHandle.py b/main/xiaozhi-server/core/handle/receiveAudioHandle.py index afe60084..c224d9a0 100644 --- a/main/xiaozhi-server/core/handle/receiveAudioHandle.py +++ b/main/xiaozhi-server/core/handle/receiveAudioHandle.py @@ -4,7 +4,7 @@ import asyncio from core.handle.abortHandle import handleAbortMessage from core.handle.intentHandler import handle_user_intent from core.utils.output_counter import check_device_output_limit -from core.utils.util import play_audio_frames, play_audio_response +from core.utils.util import audio_to_data from core.handle.sendAudioHandle import send_stt_message, SentenceType TAG = __name__ @@ -114,10 +114,13 @@ async def no_voice_close_connect(conn, have_voice): async def max_out_size(conn): + # 播放字数限制回复 + conn.client_abort = False text = "不好意思，我现在有点事情要忙，明天这个时候我们再聊，约好了哦！明天不见不散，拜拜！" await send_stt_message(conn, text) file_path = "config/assets/max_output_size.wav" - play_audio_response(conn, {"text": text, "file_path": file_path}) + opus_packets = audio_to_data(file_path) + conn.tts.tts_audio_queue.put((SentenceType.LAST, opus_packets, text)) conn.close_after_chat = True @@ -135,15 +138,16 @@ async def check_bind_device(conn): # 播放提示音 music_path = "config/assets/bind_code.wav" - conn.tts.tts_audio_queue.put((SentenceType.FIRST, [], text)) - play_audio_frames(conn, music_path) + opus_packets = audio_to_data(music_path) + conn.tts.tts_audio_queue.put((SentenceType.FIRST, opus_packets, text)) # 逐个播放数字 for i in range(6): # 确保只播放6位数字 try: digit = conn.bind_code[i] num_path = f"config/assets/bind_code/{digit}.wav" - play_audio_frames(conn, num_path) + num_packets = audio_to_data(num_path) + conn.tts.tts_audio_queue.put((SentenceType.MIDDLE, num_packets, None)) except Exception as e: conn.logger.bind(tag=TAG).error(f"播放数字音频失败: {e}") continue @@ -152,4 +156,5 @@ async def check_bind_device(conn): text = f"没有找到该设备的版本信息，请正确配置 OTA地址，然后重新编译固件。" await send_stt_message(conn, text) music_path = "config/assets/bind_not_found.wav" - play_audio_response(conn, {"text": text, "file_path": music_path}) + opus_packets = audio_to_data(music_path) + conn.tts.tts_audio_queue.put((SentenceType.LAST, opus_packets, text)) diff --git a/main/xiaozhi-server/core/utils/util.py b/main/xiaozhi-server/core/utils/util.py index 92a84bbb..26dc9fda 100644 --- a/main/xiaozhi-server/core/utils/util.py +++ b/main/xiaozhi-server/core/utils/util.py @@ -325,25 +325,6 @@ def pcm_to_data_stream(raw_data, is_opus=True, callback: Callable[[Any], Any] = frame_data = chunk if isinstance(chunk, bytes) else bytes(chunk) callback(frame_data) -def play_audio_response(conn, response): - """音频响应处理""" - conn.tts.tts_audio_queue.put((SentenceType.FIRST, [], response.get("text"))) - play_audio_frames(conn, response.get("file_path")) - conn.tts.tts_audio_queue.put((SentenceType.LAST, [], None)) - - -def play_audio_frames(conn, file_path): - """播放音频文件并处理发送帧数据""" - def handle_audio_frame(frame_data): - conn.tts.tts_audio_queue.put((SentenceType.MIDDLE, frame_data, None)) - - audio_to_data_stream( - file_path, - is_opus=True, - callback=handle_audio_frame - ) - - def opus_datas_to_wav_bytes(opus_datas, sample_rate=16000, channels=1): """ 将opus帧列表解码为wav字节流