Hi,
I am creating hypno for my self since some time now.
I thought I share the python scripts I created with AI to automate some processes.
There are 3 scripts in here:
- Multimodel Bulk Converter: for TTS and Voice Cloning
- Session Background Merger: for applying background tracks to a hypno script
- Uber Playlist: a playlist implementation that allows pauses with random length, playing files in parallel and more
You will need python 3 and pip installed to run these.
I hope the the install scripts work well other devices... On mine they ran fine.
Feel free to write post in this thread if you have problems using this.
I hope you find these useful. 😊
Multimodel Bulk Converter
Convert every `.txt` file in a folder to WAV files using either Chatterbox or VoxCPM2, then concatenate the generated sentence segments into one WAV file per input text file.
Session Background Merger
This script processes a folder of voice/session recordings and overlays each one with the same background track. It is useful when you want to create multiple sessions that all use the same music, affirmations, or ambient background without editing each file manually.
The tool:
- reads all audio files in a selected folder
- applies a fade-out and volume reduction to the background audio
- overlays each voice file at a fixed start position
- exports the processed results into a `Mastered Audio` folder
Uber Playlist
Uber Playlist is a lightweight media playback tool for creating custom audio/video playlists. It can play items in sequence or random order, insert (random) pauses, and optionally play a video alongside audio.
- Play audio and video files from a JSON playlist
- Support sequential or random playback within a section
- Optional pause duration between tracks
- Repeat controls for random playback
- Run audio and video together in parallel
- Keyboard controls for playback while the app is running
Mbc+Sbm+Up.zip (Size: 27.45 KB / Downloads: 1)
I am creating hypno for my self since some time now.
I thought I share the python scripts I created with AI to automate some processes.
There are 3 scripts in here:
- Multimodel Bulk Converter: for TTS and Voice Cloning
- Session Background Merger: for applying background tracks to a hypno script
- Uber Playlist: a playlist implementation that allows pauses with random length, playing files in parallel and more
You will need python 3 and pip installed to run these.
I hope the the install scripts work well other devices... On mine they ran fine.
Feel free to write post in this thread if you have problems using this.
I hope you find these useful. 😊
Multimodel Bulk Converter
Convert every `.txt` file in a folder to WAV files using either Chatterbox or VoxCPM2, then concatenate the generated sentence segments into one WAV file per input text file.
Session Background Merger
This script processes a folder of voice/session recordings and overlays each one with the same background track. It is useful when you want to create multiple sessions that all use the same music, affirmations, or ambient background without editing each file manually.
The tool:
- reads all audio files in a selected folder
- applies a fade-out and volume reduction to the background audio
- overlays each voice file at a fixed start position
- exports the processed results into a `Mastered Audio` folder
Uber Playlist
Uber Playlist is a lightweight media playback tool for creating custom audio/video playlists. It can play items in sequence or random order, insert (random) pauses, and optionally play a video alongside audio.
- Play audio and video files from a JSON playlist
- Support sequential or random playback within a section
- Optional pause duration between tracks
- Repeat controls for random playback
- Run audio and video together in parallel
- Keyboard controls for playback while the app is running
Mbc+Sbm+Up.zip (Size: 27.45 KB / Downloads: 1)
