The initial launch should download the default model.
If there's a problem with the initial download, you can download the needed files from: xTTS-V2 (you need to download: config.json, model.pth, speakers_xtts.pth, vocab.json).
This is how your xtts_model folder should look like :
Hi guys I have an RTX 5080 that isn't supported by the distributed PyTorch version. I tried to force a PyTorch upgrade using pip3 inside the internal XTTS folder but then the server crashes on startup. When I try to launch it via command it acts like a new install (and will probably overwrite the updated PyTorch files). Any ideas on how to make it work? Thanks
Just got my new rig today, exact same card, exact same problem, womp womp...
Update: After digging it could in theory be possible to run XTTS CPU bound by enabling CUDA_LAUNCH_BLOCKING=1 but I would probably advise against it as it is intended for debugging purposes and may do more harm than good so unless NVIDA finally decides to add CUDA support for the latest version of PyTorch we are SOL so to speak.
Does anyone know if there is a video that explains how to create the custom voice model for an NPC? I followed the written instructions with the WAV audio but I can't get the JSON file to generate.
I have just achieved Chinese speech synthesis, but the speed is extremely slow. Can Mantella support the large-scale streaming speech recognition model?
I have XTTS working on a remote PC. (Very useful app BTW) Along with that I have LM Studio. Both are working fine with MGO 3.5.2 on a different PC. The XTTS PC has a 3090Ti w 24gb of VRAM. The PC's also have 5gb/s NIC's on a 10gb switch. I was wondering if there are any tweaks that can be used to help performance of XTTS? According to the Mantella deployment guide XTTS is slower than Piper but has much better features. Any tips on tweaking for performance?
Hi, at the moment of try to use the mod i get this message from the mantella cmd
21:37:51.738 TTS: Connecting to XTTS... 21:37:53.772 TTS: Could not connect to XTTS. Attempting to run headless server... Traceback (most recent call last): File "PyInstaller\hooks\rthooks\pyi_rth_win32comgenpy.py", line 46, in <module> File "PyInstaller\hooks\rthooks\pyi_rth_win32comgenpy.py", line 25, in _pyi_rthook File "PyInstaller\loader\pyimod02_importers.py", line 419, in exec_module File "win32com\__init__.py", line 8, in <module> File "PyInstaller\loader\pyimod02_importers.py", line 419, in exec_module File "pythoncom.py", line 2, in <module> import pywintypes File "PyInstaller\loader\pyimod02_importers.py", line 419, in exec_module File "pywintypes.py", line 126, in <module> File "pywintypes.py", line 47, in __import_pywin32_system_module__ ImportError: Module 'pywintypes' isn't in frozen sys.path ['D:\\user\\xtts_mantella_api_server-113445-1-5-1725725632\\_internal\\base_library.zip', 'D:\\user\\xtts_mantella_api_server-113445-1-5-1725725632\\_internal\\lib-dynload', 'D:\\user\\xtts_mantella_api_server-113445-1-5-1725725632\\_internal'] [9744] Failed to execute script 'pyi_rth_win32comgenpy' due to unhandled exception!
Help please, i have an error message in Mantella that says: Waiting for player to select an NPC... 05:58:39.541 INFO: generated new fontManager 05:59:06.968 INFO: Running LLM with OpenAI Running Mantella with 'gpt-4o-mini'. The language model can be changed in MantellaSoftware/config.ini 05:59:08.563 TTS: Connecting to XTTS... 05:59:10.611 TTS: Could not connect to XTTS. Attempting to run headless server... "C:/Users/Solid" no se reconoce como un comando interno o externo, programa o archivo por lotes ejecutable.
Descargue todo me va bien pero a la hora de que me respondan los npcs me responden en español pero con acento ingles y ya descargue las voces en español
Puede que sea debido a la configuración de Mantella en si, con el juego en marcha Mantella abre una pestaña de navegador con sus opciones de configuración, asegúrate de que en la sección de text to speech el motor seleccionado es XTTS y no Pipe (que es el que viene por defecto con ese acento tan cómico)
Is there a way how to make work also added voice models in hosting runpod? I could run them only locally. If they are used by hosted pod I am receiving error notice about missing voice model.
98 comments
If there's a problem with the initial download, you can download the needed files from: xTTS-V2 (you need to download: config.json, model.pth, speakers_xtts.pth, vocab.json).
This is how your xtts_model folder should look like :
└── xtts_models/ |
└── v2.0.2/
├── config.json
├── model.pth
├── speakers_xtts.pth
└── vocab.json
I have an RTX 5080 that isn't supported by the distributed PyTorch version. I tried to force a PyTorch upgrade using pip3 inside the internal XTTS folder but then the server crashes on startup. When I try to launch it via command it acts like a new install (and will probably overwrite the updated PyTorch files).
Any ideas on how to make it work?
Thanks
Update: After digging it could in theory be possible to run XTTS CPU bound by enabling CUDA_LAUNCH_BLOCKING=1 but I would probably advise against it as it is intended for debugging purposes and may do more harm than good so unless NVIDA finally decides to add CUDA support for the latest version of PyTorch we are SOL so to speak.
exp. https://www.volcengine.com/docs/6561/1354869
The demo
5.35 07/12 [email protected] dNw:/ 当VR角色扮演游戏集成了Ai # RPG # 上古卷轴 # Ai 带上VR，打开了新世界大门，游戏还可以这么玩。 https://v.douyin.com/i5Q62MAn/ 复制此链接，打开Dou音搜索，直接观看视频！
Thx, and well done.
21:37:51.738 TTS: Connecting to XTTS...
21:37:53.772 TTS: Could not connect to XTTS. Attempting to run headless server...
Traceback (most recent call last):
File "PyInstaller\hooks\rthooks\pyi_rth_win32comgenpy.py", line 46, in <module>
File "PyInstaller\hooks\rthooks\pyi_rth_win32comgenpy.py", line 25, in _pyi_rthook
File "PyInstaller\loader\pyimod02_importers.py", line 419, in exec_module
File "win32com\__init__.py", line 8, in <module>
File "PyInstaller\loader\pyimod02_importers.py", line 419, in exec_module
File "pythoncom.py", line 2, in <module>
import pywintypes
File "PyInstaller\loader\pyimod02_importers.py", line 419, in exec_module
File "pywintypes.py", line 126, in <module>
File "pywintypes.py", line 47, in __import_pywin32_system_module__
ImportError: Module 'pywintypes' isn't in frozen sys.path ['D:\\user\\xtts_mantella_api_server-113445-1-5-1725725632\\_internal\\base_library.zip', 'D:\\user\\xtts_mantella_api_server-113445-1-5-1725725632\\_internal\\lib-dynload', 'D:\\user\\xtts_mantella_api_server-113445-1-5-1725725632\\_internal']
[9744] Failed to execute script 'pyi_rth_win32comgenpy' due to unhandled exception!
Waiting for player to select an NPC...
05:58:39.541 INFO: generated new fontManager
05:59:06.968 INFO: Running LLM with OpenAI
Running Mantella with 'gpt-4o-mini'. The language model can be changed in MantellaSoftware/config.ini
05:59:08.563 TTS: Connecting to XTTS...
05:59:10.611 TTS: Could not connect to XTTS. Attempting to run headless server...
"C:/Users/Solid" no se reconoce como un comando interno o externo,
programa o archivo por lotes ejecutable.
I need help please, why?