Hass/xiaozhi-esp32-server
1
0
Fork 0
mirror of https://github.com/xinnan-tech/xiaozhi-esp32-server.git synced 2026-07-22 07:03:53 +08:00
Code Issues Packages Projects Releases Wiki Activity

update:更新paddlespeech.py

Browse Source
This commit is contained in:
FAN-yeB
2025-08-13 16:00:33 +08:00
parent bda6c1e3ed
commit 7e63e1d607
1 changed files with 14 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
main/xiaozhi-server/core/providers/tts/paddle_speech.py
+14 -4
View File
@@ -18,10 +18,20 @@ class TTSProvider(TTSProviderBase):
super().__init__(config, delete_audio_file)
self.url = config.get("url", "ws://192.168.1.10:8092/paddlespeech/tts/streaming")
self.protocol = config.get("protocol", "websocket")
self.spk_id = config.get("spk_id", 0)
self.sample_rate = config.get("sample_rate", 24000)
self.speed = config.get("speed", 1.0)
self.volume = config.get("volume", 1.0)
if config.get("private_voice"):
self.spk_id = int(config.get("private_voice"))
else:
self.spk_id = int(config.get("spk_id", "0"))
sample_rate = config.get("sample_rate", 24000)
self.sample_rate = float(sample_rate) if sample_rate else 24000
speed = config.get("speed", 1.0)
self.speed = float(speed) if speed else 1.0
volume = config.get("volume", 1.0)
self.volume = float(volume) if volume else 1.0
self.save_path = config.get("save_path", "./streaming_tts.wav")
async def pcm_to_wav(self, pcm_data: bytes, sample_rate: int = 24000, num_channels: int = 1,