Skip to content

Product Outputs 🤖

Explanation of Terms and Outputs in CreatorBox

Directory Description

Explanation of subdirectories and files under the CreatorBox folder

├models Models
├src    Code
├static Static Resources
├webapp Output Directory
├─cache Cache
│      llm.db                          Large Model Cache Data

├─data Data
│      gradio.json                     Application Mount Data
│      settings.json                   User Preferences
│      speaker.json                    User Voice Data
│      token.json                      User Login credentials

├─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                    Audio, Format: (Index.wav)
│      │      .....
│      │      test.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
│      │      test_vocals.wav          Speaker's Voice
│      │      test_instrumental.wav    Background Instrumental
│      │      
│      ├─tts  Text-to-Speech Folder
│      │      00_c94f3e.wav            Audio, Format: (Index:2d_MD5.wav)
│      │      .....
│      │      test.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 Data

Model Directory

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

  • Custom download location can be specified using the CREATORBOX_MODEL environment variable.

.models
├─creatorbox
│  ├─vur
│  └─vmr

├─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
│  └─models
│      └─iic
│          ├─CosyVoice2-0.5B
│          ├─CosyVoice2-0___5B
│          .....