FAQ ❓
Word count
1106 words
Reading time
7 minutes
Summary of common issues during installation and usage
Network
Please ensure your network is working properly. VPN needs to be enabled in
global mode.Environment dependencies will be downloaded and configured automatically during installation; no manual intervention is required.
Model files use an on-demand download mechanism: they are only downloaded when actually used.
Outputs
Directory Description
Explanation of subdirectories and files under the CreatorBox folder
├extensions Extensions
├models Models
├src Code
├static Static Resources
├webapp Output Directory
│
├─cache Cache
│ llm Large Model Cache Data
│
├─data Data
│ db.db Application Data
│ settings.json User Preferences
│
├─extensions Extensions
│ ... Configuration required for corresponding extensions
│
├─logs Logs
│ creator_2025-01-01.log Runtime Logs
│
├─spk Speaker Voices
│ MacArthur.wav Custom Voice Clip
│
├─temp Temporary
│ └─test Video Directory
│ │ test.jpg Source Cover
│ │ test.mp4 Source Video (This video originates from `upload` and does not affect the source video)
│ │ test.srt Source Subtitles
│ │ test.wav Source Audio
│ │ test_en.json Final Data, Format: (Filename_Identifier.json)
│ │ test_en.mp4 Final Video, Format: (Filename_Identifier.mp4)
│ │ test_en.srt Final Subtitles, Format: (Filename_Identifier.srt)
│ │ test_en.wav Final Audio, Format: (Filename_Identifier.wav)
│ │
│ ├─dubbing Dubbing Folder
│ │ 0.wav Segment, Format: (Index.wav)
│ │ .....
│ │ test.wav Audio, Format: (Index.wav)
│ │
│ ├─json Data Folder
│ │ test_draft_content.json Draft Output from Editing Software
│ │ test_draft_input.json Draft Content Input
│ │ test_asr.json Audio Transcription Data
│ │
│ ├─stems Audio Separation Folder
│ │ vocals.wav Speaker's Voice
│ │ test_instrumental.wav Background Instrumental
│ │
│ ├─tts Text-to-Speech Folder
│ │ 00_c94f3e.wav Segment, Format: (Index:2d_MD5.wav)
│ │ .....
│ │ test.wav Audio, Format: (Index:2d_MD5.wav)
│ │
│ ├─voices Voice Processing Folder
│ │ 0.wav Audio, Format: (Index.wav)
│
├─tts Audition
│ cosy_SiMei_1.0_105_0.wav Audition Audio for Character `Si Mei`
│ ...
│
├─upload Upload
│ test.mp4 Uploaded Video
│
├─download Download
│ youtube-video.mp4 Downloaded Video
│ youtube-video.json Downloaded Video DataModel Directory
On the first run, models will be automatically downloaded to the
modelsdirectory.You can customize the download location by specifying it via the
CREATORBOX_MODELenvironment variable or in the/settingspage. The changes will take effect after a restart.
.models
├─creatorbox
│ ├─dh
│ └─uvr
│
├─huggingface
│ └─hub
│ ├─.locks
│ ├─models--SWivid--F5-TTS
│ ├─models--charactr--vocos-mel-24khz
│ ├─models--pyannote--segmentation-3.0
│ ├─models--pyannote--speaker-diarization-3.1
│ ├─models--pyannote--wespeaker-voxceleb-resnet34-LM
│ ├─models--Systran--faster-whisper-base
│ ├─models--Systran--faster-whisper-large-v2
│ └─models--Systran--faster-whisper-medium
│ .....
│
├─modelscope
│ └─iic
│ ├─CosyVoice3-0.5B
│ ├─emotion2vec
│ .....
│
├─torch
│ └─hub
│ ├─big-lama.pt
│ .....Installation
Graphics card usage
Solution
Currently only supports NVIDIA cards.
Reference Configuration
cmd
nvidia-smi
logs
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2024 NVIDIA Corporation
Built on Thu_Jun__6_02:18:23_PDT_2024
Cuda compilation tools, release 12.5, V12.5.82
Build cuda_12.5.r12.5/compiler.34385749_0
Sat Jul 12 14:42:54 2025
+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 560.35.03 Driver Version: 560.35.03 CUDA Version: 12.6 |
|---------------------------------------+------------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=======================================+========================+======================|
| 0 Tesla T4 Off | 00000000:00:04.0 Off | 0 |
| N/A 39C P8 9W / 70W | 1MiB / 15360MiB | 0% Default |
| | | N/A |
+---------------------------------------+------------------------+----------------------+
| 1 Tesla T4 Off | 00000000:00:05.0 Off | 0 |
| N/A 41C P8 9W / 70W | 1MiB / 15360MiB | 0% Default |
| | | N/A |
+---------------------------------------+------------------------+----------------------+Reference Version
2.6.0+cu124
bash
uv pip install torch==2.6.0+cu124 torchvision==0.21.0+cu124 torchaudio==2.6.0+cu124 --extra-index-url https://download.pytorch.org/whl/cu124
uv pip install torch==2.6.0+cu124 torchvision==0.21.0+cu124 torchaudio==2.6.0+cu124 --extra-index-url https://mirrors.nju.edu.cn/pytorch/whl/cu1242.6.0+cu126
bash
uv pip install torch==2.6.0+cu126 torchvision==0.21.0+cu126 torchaudio==2.6.0+cu126 --extra-index-url https://download.pytorch.org/whl/cu126
uv pip install torch==2.6.0+cu126 torchvision==0.21.0+cu126 torchaudio==2.6.0+cu126 --extra-index-url https://mirrors.nju.edu.cn/pytorch/whl/cu126...
Startup
Startup Error
Solution
- If you see
RuntimeError: this license key is expired, try forcing an update:
bash
git pull- If you see
RuntimeError: [WinError 10060]...(1:11076), Please try restarting:
bash
uv run --extra {gpu|cpu} cli.py start- For
Windows, simply double-clickstart.bator create a desktop shortcut to run it. Please adjust the environment settings according to your actual configuration.
bash
REM Execute script
set SCRIPT_CMD=uv run --extra gpu
set SCRIPT_PATH=cli.py
set SCRIPT_ARGS=start -h 0.0.0.0 -p 8000
if "%~1"=="--debug" (
set SCRIPT_ARGS=%SCRIPT_ARGS% --debug
)- runs on
cpuby default. To usegpu, you need to add the--extra gpuparameter.
Startup Venv
Solution
Command startup requires pre-activating the environment in cmd. Using D:\Program Files\CreatorBox as an example:
- Default Environment
bash
D: & cd "D:\Program Files\CreatorBox\creatorbox" & "D:\Program Files\CreatorBox\creatorbox\.venv\Scripts\activate.bat"- Extended Environment
bash
# index_tts
D: & cd "D:\Program Files\CreatorBox\creatorbox\extensions\index_tts" & "D:\Program Files\CreatorBox\creatorbox\extensions\index_tts\.venv\Scripts\activate.bat"
# cosyvoice
D: & cd "D:\Program Files\CreatorBox\creatorbox\extensions\cosyvoice" & "D:\Program Files\CreatorBox\creatorbox\extensions\cosyvoice\.venv\Scripts\activate.bat"
# gpt_sovits
D: & cd "D:\Program Files\CreatorBox\creatorbox\extensions\gpt_sovits" & "D:\Program Files\CreatorBox\creatorbox\extensions\gpt_sovits\.venv\Scripts\activate.bat"
...Expected Output
log
(creatorbox) D:\Program Files\CreatorBox\creatorbox>
(index_tts) D:\Program Files\CreatorBox\creatorbox\extensions\index_tts>
(cosyvoice) D:\Program Files\CreatorBox\creatorbox\extensions\cosyvoice>
(gpt_sovits) D:\Program Files\CreatorBox\creatorbox\extensions\gpt_sovits>
...Then enter the command
Usage
The device is not ready
Solution
log
PermissionError: [WinError 21] The device is not readyIf installed on the system drive, you need to run as administrator. Not recommended.
Dubbing languages
Usage
10 languages are built in by default, and the browser's preferred language setting is used by default. Custom nodes can also be added.
json
{
"locales": [
{
"name": "中国",
"locale": "zh-CN",
"country": "China",
"enable": true
}
]
// ...
}Vpn Usage Error
Solution
log
Retrying 1 time(s), translation_json ->
Your location is not supported by google-generativeai at the moment. Try to use ChatVertexAI LLM from langchain_google_vertexai., waiting 5.0 seconds before retrying.- If you see a message like
Your location is not supported, it means your IP address is blocked. Try switching to a different proxy region.. - Recommend Proxy, see the 《JustMySocks》 section.
Ngrok Usage Error
Solution
log
PyngrokNgrokError:
The ngrok process errored on start: authentication failed:
Your account is limited to 1 simultaneous ngrok agent sessions.
You can run multiple simultaneous tunnels from a single agent session by defining the tunnels in your agent configuration file and starting them with the command `ngrok start --all`.
Read more about the agent configuration file: https://ngrok.com/docs/secure-tunnels/ngrok-agent/reference/config
You can view your current agent sessions in the dashboard:
https://dashboard.ngrok.com/agents ERR_NGROK_108.If the above error occurs, go to the Ngrok Dashboard at https://dashboard.ngrok.com/agents, terminate the running agent, and retry run
Model
Model Download Failure
Solution
log
An error occured while synchronizing the model Systran/faster-whisper-large-v3 from the Hugging Face Hub:
An error happened while trying to locate the files on the Hub and we cannot find the appropriate snapshot folder for the
specified revision on the local disk. Please check your internet connection and try again.
Trying to load the model directly from the local cache, if it exists.Speaker Invocation Error
Solution
log
2025-04-18 07:29:31.094 | INFO whisper_.py:102 - Loading Speaker model on device cuda
2025-04-18 07:29:31.865 | ERROR whisper_.py:106 - Error: 401 Client Error: Unauthorized for url: https://hf-mirror.com/pyannote/speaker-diarization-3.1/resolve/main/config.yaml (Request ID: Root=1-6801ff5b-0270fbd846adbc761e229ace;fddee4c5-7f49-4739-bba3-42cbc47dca6e)- Go to and accept the user agreement for
pyannote/segmentation-3.0 - Accept the user agreement for
pyannote/speaker-diarization-3.1 - Go to and obtain an access token:
huggingface.co/settings/tokens