Hass/xiaozhi-esp32-server
1
0
Fork 0
mirror of https://github.com/xinnan-tech/xiaozhi-esp32-server.git synced 2026-07-30 05:13:59 +08:00
Code Issues Packages Projects Releases Wiki Activity

update：格式化代码

Browse Source
This commit is contained in:
hrz
2025-04-01 14:27:17 +08:00
parent d9d973b6aa 7c389a0641
commit 61db1192e2
7 changed files with 507 additions and 222 deletions
Download Patch File Download Diff File Expand all files Collapse all files
main/xiaozhi-server/core/providers/tts/edge.py
+22 -6
View File
@@ -13,17 +13,23 @@ from core.providers.tts.dto.dto import TTSMessageDTO, MsgType, SentenceType
TAG = __name__
logger = setup_logging()
class TTSProvider(TTSProviderBase):
def __init__(self, config, delete_audio_file):
super().__init__(config, delete_audio_file)
self.voice = config.get("voice")
def generate_filename(self, extension=".mp3"):
return os.path.join(self.output_file, f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}")
return os.path.join(
self.output_file,
f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}",
)
async def text_to_speak(self, u_id, text, is_last_text=False, is_first_text=False):
try:
communicate = edge_tts.Communicate(text, voice=self.voice) # Use your preferred voice
communicate = edge_tts.Communicate(
text, voice=self.voice
) # Use your preferred voice
tmp_file = self.generate_filename()
await communicate.save(tmp_file)
@@ -31,7 +37,13 @@ class TTSProvider(TTSProviderBase):
audio = AudioSegment.from_file(tmp_file, format="mp3")
audio = audio.set_channels(1).set_frame_rate(16000)
opus_datas = self.wav_to_opus_data_audio_raw(audio.raw_data)
yield TTSMessageDTO(u_id=u_id, msg_type=MsgType.TTS_TEXT_RESPONSE, content=opus_datas, tts_finish_text=text,sentence_type=SentenceType.SENTENCE_START)
yield TTSMessageDTO(
u_id=u_id,
msg_type=MsgType.TTS_TEXT_RESPONSE,
content=opus_datas,
tts_finish_text=text,
sentence_type=SentenceType.SENTENCE_START,
)
# 用完后删除临时文件
try:
os.remove(tmp_file)
@@ -40,6 +52,10 @@ class TTSProvider(TTSProviderBase):
pass
except Exception as e:
logger.bind(tag=TAG).error(f"TTSProvider text_to_speak error: {e}")
yield TTSMessageDTO(u_id=u_id, msg_type=MsgType.TTS_TEXT_RESPONSE, content=[], tts_finish_text=text,sentence_type=SentenceType.SENTENCE_START)
yield TTSMessageDTO(
u_id=u_id,
msg_type=MsgType.TTS_TEXT_RESPONSE,
content=[],
tts_finish_text=text,
sentence_type=SentenceType.SENTENCE_START,
)