How to use custom TTS?

[SuperMaximus1984]

RedTheDocs of this project says I can run with CLI syntax like below: python app.py --tts gpt-sovits --TTS_SERVER http://127.0.0.1:8080 --REF_FILE ref.wav --REF_TEXT xxx

But then I face the error 'LipReal' object has no attribute 'tts' or AttributeError: 'NeRFReal' object has no attribute 'tts' depending on the model I choose.

My fishTTS is up & running on http://127.0.0.1:8080, OpenAPI is hooked up, but LiveTalking docker container throws the above errors when I press WebUI "Start" button.

Please help to run with custom TTS. Thank you!

[liuxiaohan00]

python app.py --tts gpt-sovits --TTS_SERVER http://127.0.0.1:8080 --REF_FILE ref.wav --REF_TEXT xxx --tts后面参数错了吧，按照这个来： if opt.tts == "edgetts": self.tts = EdgeTTS(opt,self) elif opt.tts == "gpt-sovits": self.tts = VoitsTTS(opt,self) elif opt.tts == "xtts": self.tts = XTTS(opt,self) elif opt.tts == "cosyvoice": self.tts = CosyVoiceTTS(opt,self) elif opt.tts == "fishtts": self.tts = FishTTS(opt,self) elif opt.tts == "tencent": self.tts = TencentTTS(opt,self)

[byronv5]

我用腾讯语音：python app.py --transport webrtc --model musetalk --avatar_id avator_4 --max_session 10 --tts tencent --REF_FILE 601002 点击开始也报错： DEBUG:logger:HumanPlayer Starting worker thread Exception in thread media-player: Traceback (most recent call last): File "/root/miniconda3/envs/nerfstream/lib/python3.10/threading.py", line 1016, in _bootstrap_inner self.run() File "/root/miniconda3/envs/nerfstream/lib/python3.10/threading.py", line 953, in run self._target(*self._args, **self._kwargs) File "/workspace/LiveTalking/webrtc.py", line 161, in player_worker_thread container.render(quit_event,loop,audio_track,video_track) File "/workspace/LiveTalking/musereal.py", line 327, in render self.tts.render(quit_event) AttributeError: 'MuseReal' object has no attribute 'tts'

[byronv5]

我用腾讯语音：python app.py --transport webrtc --model musetalk --avatar_id avator_4 --max_session 10 --tts tencent --REF_FILE 601002 点击开始也报错： DEBUG:logger:HumanPlayer Starting worker thread Exception in thread media-player: Traceback (most recent call last): File "/root/miniconda3/envs/nerfstream/lib/python3.10/threading.py", line 1016, in _bootstrap_inner self.run() File "/root/miniconda3/envs/nerfstream/lib/python3.10/threading.py", line 953, in run self._target(*self._args, **self._kwargs) File "/workspace/LiveTalking/webrtc.py", line 161, in player_worker_thread container.render(quit_event,loop,audio_track,video_track) File "/workspace/LiveTalking/musereal.py", line 327, in render self.tts.render(quit_event) AttributeError: 'MuseReal' object has no attribute 'tts'

但我最后发现，我用的镜像中并没有TencentTTS，加上就好了