FAQ

Word count

1143 words

Reading time

8 minutes

Summary of installation and usage issues

Outputs

Project Directory new

Explanation of directories and files under the CreatorBox folder

• webapp Webapp Directory
  • cache Cache
  • data Data
  • download Download
  • dubb Dubbing
    • test Video Folder
      • _v1 Output Directory
      • draft Draft Folder
      • stems Audio Separation
      • voices Voice Processing
      • test.mp4 Source Video
      • test.png Source Cover
      • test.srt Source Subtitles
      • test.wav Source Audio
  • extensions Extensions
  • logs Logs
  • sample Sample
  • spk Voices
  • temp Temporary
  • tts TTS
  • upload Upload

Model Directory new

Explanation of directories

• models
  • creatorbox
  • huggingface
  • modelscope
  • torch

• On the first run, models will be automatically downloaded to the models directory.

• You can customize the download location by specifying it via the CREATORBOX_MODEL environment variable or in the /settings page. The changes will take effect after a restart.

Installation

Graphics card usage new

Currently only supports NVIDIA GPUs, Official Download | Mirror Download

Reference versions

• 2.6.0+cu126

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

Reference configuration

nvidia-smi

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 |
+---------------------------------------+------------------------+----------------------+

Startup

Startup Error

Solution

• If you see RuntimeError: this license key is expired, try forcing an update:

# git reset --hard
# git clean -fd
git pull

• For Windows, simply double-click start.bat or create a desktop shortcut to run it. Please adjust the environment settings according to your actual configuration.

creatorbox/start.bat

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 cpu by default. To use gpu, you need to add the --extra gpu parameter.

Startup Venv

Solution

Command startup requires pre-activating the environment. Using D:\Program Files\CreatorBox as an example:

• Default Environment

D:; cd "D:\Program Files\CreatorBox\creatorbox"; .\.venv\Scripts\activate.ps1

• Extended Environment

# iopaint
D:; & cd "D:\Program Files\CreatorBox\creatorbox\extensions\iopaint"; .\.venv\Scripts\activate.ps1
# voxcpm
D:; & cd "D:\Program Files\CreatorBox\creatorbox\extensions\voxcpm"; .\.venv\Scripts\activate.ps1
# index_tts
D:; & cd "D:\Program Files\CreatorBox\creatorbox\extensions\index_tts"; .\.venv\Scripts\activate.ps1
# cosyvoice
D:; & cd "D:\Program Files\CreatorBox\creatorbox\extensions\cosyvoice"; .\.venv\Scripts\activate.ps1
# gpt_sovits
D:; & cd "D:\Program Files\CreatorBox\creatorbox\extensions\gpt_sovits"; .\.venv\Scripts\activate.ps1

Expected Output

(creatorbox) PS D:\Program Files\CreatorBox\creatorbox>
(iopaint) PS D:\Program Files\CreatorBox\creatorbox\extensions\voxcpm
(index_tts) PS D:\Program Files\CreatorBox\creatorbox\extensions\index_tts>
(cosyvoice) PS D:\Program Files\CreatorBox\creatorbox\extensions\cosyvoice>
(gpt_sovits) PS D:\Program Files\CreatorBox\creatorbox\extensions\gpt_sovits>

• The main environment and extended environments are isolated. If environment dependencies are incompatible, you can install dependencies in the corresponding environment without affecting other environments.
• (xxx) The name in parentheses is the current environment, followed by the current path
• Ending with > indicates the current path is where the environment is located. Commands executed in this path will run in the current environment.
• Recommend using the Windows Terminal.

Usage

Request Expired new

Solution

When this error occurs during login/registration, click 'Forgot Password'. After receiving the email, reset your password and log in again.

The device is not ready

Solution

PermissionError: [WinError 21] The device is not ready

If installed on the system drive, you need to run as administrator. Not recommended.

Multilingual configuration

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.

webapp\data\settings.json

{
    "locales": [
        {
            "name": "中国",
            "locale": "zh-CN",
            "country": "China",
            "enable": true
        }
    ]
    // ...
}

Vpn Error

Solution

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 Error

Solution

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

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.

Download models via domestic mirror

Speaker Invocation Error

Solution

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)

1. Go to and accept the user agreement for pyannote/segmentation-3.0
2. Accept the user agreement for pyannote/speaker-diarization-3.1
3. Go to and obtain an access token: huggingface.co/settings/tokens