diff --git a/main/xiaozhi-server/core/handle/helloHandle.py b/main/xiaozhi-server/core/handle/helloHandle.py index e4e836b4..c4f55841 100644 --- a/main/xiaozhi-server/core/handle/helloHandle.py +++ b/main/xiaozhi-server/core/handle/helloHandle.py @@ -83,7 +83,7 @@ async def checkWakeupWords(conn, text): # 播放唤醒词回复 conn.client_abort = False - opus_packets, _ = audio_to_data(response.get("file_path")) + opus_packets = audio_to_data(response.get("file_path")) conn.logger.bind(tag=TAG).info(f"播放唤醒词回复: {response.get('text')}") await sendAudioMessage(conn, SentenceType.FIRST, opus_packets, response.get("text")) diff --git a/main/xiaozhi-server/core/handle/receiveAudioHandle.py b/main/xiaozhi-server/core/handle/receiveAudioHandle.py index e6f39632..174c8b2b 100644 --- a/main/xiaozhi-server/core/handle/receiveAudioHandle.py +++ b/main/xiaozhi-server/core/handle/receiveAudioHandle.py @@ -140,7 +140,7 @@ async def check_bind_device(conn): # 播放提示音 music_path = "config/assets/bind_code.wav" - opus_packets, _ = audio_to_data(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 @@ -148,7 +148,7 @@ async def check_bind_device(conn): try: digit = conn.bind_code[i] num_path = f"config/assets/bind_code/{digit}.wav" - num_packets, _ = audio_to_data(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}") @@ -158,5 +158,5 @@ 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" - opus_packets, _ = audio_to_data(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/providers/tts/base.py b/main/xiaozhi-server/core/providers/tts/base.py index 40570326..87bb64f6 100644 --- a/main/xiaozhi-server/core/providers/tts/base.py +++ b/main/xiaozhi-server/core/providers/tts/base.py @@ -86,7 +86,7 @@ class TTSProviderBase(ABC): try: audio_bytes = asyncio.run(self.text_to_speak(text, None)) if audio_bytes: - audio_datas, _ = audio_bytes_to_data( + audio_datas = audio_bytes_to_data( audio_bytes, file_type=self.audio_file_type, is_opus=True ) return audio_datas @@ -334,11 +334,11 @@ class TTSProviderBase(ABC): tuple: (sentence_type, audio_datas, content_detail) """ if tts_file.endswith(".p3"): - audio_datas, _ = p3.decode_opus_from_file(tts_file) + audio_datas = p3.decode_opus_from_file(tts_file) elif self.conn.audio_format == "pcm": - audio_datas, _ = self.audio_to_pcm_data(tts_file) + audio_datas = self.audio_to_pcm_data(tts_file) else: - audio_datas, _ = self.audio_to_opus_data(tts_file) + audio_datas = self.audio_to_opus_data(tts_file) if ( self.delete_audio_file diff --git a/main/xiaozhi-server/core/utils/p3.py b/main/xiaozhi-server/core/utils/p3.py index c75b968e..f196da0b 100644 --- a/main/xiaozhi-server/core/utils/p3.py +++ b/main/xiaozhi-server/core/utils/p3.py @@ -5,10 +5,6 @@ def decode_opus_from_file(input_file): 从p3文件中解码 Opus 数据，并返回一个 Opus 数据包的列表以及总时长。 """ opus_datas = [] - total_frames = 0 - sample_rate = 16000 # 文件采样率 - frame_duration_ms = 60 # 帧时长 - frame_size = int(sample_rate * frame_duration_ms / 1000) with open(input_file, 'rb') as f: while True: @@ -26,11 +22,8 @@ def decode_opus_from_file(input_file): raise ValueError(f"Data length({len(opus_data)}) mismatch({data_len}) in the file.") opus_datas.append(opus_data) - total_frames += 1 - # 计算总时长 - total_duration = (total_frames * frame_duration_ms) / 1000.0 - return opus_datas, total_duration + return opus_datas def decode_opus_from_bytes(input_bytes): """ @@ -38,10 +31,6 @@ def decode_opus_from_bytes(input_bytes): """ import io opus_datas = [] - total_frames = 0 - sample_rate = 16000 # 文件采样率 - frame_duration_ms = 60 # 帧时长 - frame_size = int(sample_rate * frame_duration_ms / 1000) f = io.BytesIO(input_bytes) while True: @@ -53,7 +42,5 @@ def decode_opus_from_bytes(input_bytes): if len(opus_data) != data_len: raise ValueError(f"Data length({len(opus_data)}) mismatch({data_len}) in the bytes.") opus_datas.append(opus_data) - total_frames += 1 - total_duration = (total_frames * frame_duration_ms) / 1000.0 - return opus_datas, total_duration \ No newline at end of file + return opus_datas \ No newline at end of file diff --git a/main/xiaozhi-server/core/utils/util.py b/main/xiaozhi-server/core/utils/util.py index ce6f20ea..641e2655 100644 --- a/main/xiaozhi-server/core/utils/util.py +++ b/main/xiaozhi-server/core/utils/util.py @@ -224,12 +224,9 @@ def audio_to_data(audio_file_path, is_opus=True): # 转换为单声道/16kHz采样率/16位小端编码（确保与编码器匹配） audio = audio.set_channels(1).set_frame_rate(16000).set_sample_width(2) - # 音频时长(秒) - duration = len(audio) / 1000.0 - # 获取原始PCM数据（16位小端） raw_data = audio.raw_data - return pcm_to_data(raw_data, is_opus), duration + return pcm_to_data(raw_data, is_opus) def audio_bytes_to_data(audio_bytes, file_type, is_opus=True): @@ -245,9 +242,8 @@ def audio_bytes_to_data(audio_bytes, file_type, is_opus=True): BytesIO(audio_bytes), format=file_type, parameters=["-nostdin"] ) audio = audio.set_channels(1).set_frame_rate(16000).set_sample_width(2) - duration = len(audio) / 1000.0 raw_data = audio.raw_data - return pcm_to_data(raw_data, is_opus), duration + return pcm_to_data(raw_data, is_opus) def pcm_to_data(raw_data, is_opus=True):