https://github.com/codefromanywhere/ai-creative
https://github.com/codefromanywhere/ai-creative
Last synced: 10 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/codefromanywhere/ai-creative
- Owner: CodeFromAnywhere
- Created: 2023-09-05T06:20:28.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2023-09-05T07:58:20.000Z (over 2 years ago)
- Last Synced: 2024-11-28T21:05:09.697Z (about 1 year ago)
- Language: TypeScript
- Size: 229 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: readme.md
Awesome Lists containing this project
README
# Ai music
ai-music (`OperationClassification` undefined)
# Api reference
## generateRap()
This is a plugin!
TODO:
- Make it possible to send out a template to the masses, preferably with a personal followup message and possibly some free messages. Ensure it's possible to filter on country as well to save money.
MAKE IT MP4 WITH SUBTITLES
- continue song until the end after rap is done
- check length of audio
- whisper audio to get srt
- create video with single image of the artist for the duration of the song (pick a AI generated art image)
- add the audio to the video
- add hard subtitles to the video (see https://www.bannerbear.com/blog/how-to-add-subtitles-to-a-video-file-using-ffmpeg/)
- don't output the lyrics anymore, just the video is enough
- store the video in the persons memory
| Input | | |
| ---------- | -- | -- |
| chatContext | `ChatContext` | |,| chatMessage | `CreateOrmItem` | |,| truncatedMessageHistory | `CreateOrmItem`[] | |
| **Output** | | |
## 📄 generateRap (exported const)
This is a plugin!
TODO:
- Make it possible to send out a template to the masses, preferably with a personal followup message and possibly some free messages. Ensure it's possible to filter on country as well to save money.
MAKE IT MP4 WITH SUBTITLES
- continue song until the end after rap is done
- check length of audio
- whisper audio to get srt
- create video with single image of the artist for the duration of the song (pick a AI generated art image)
- add the audio to the video
- add hard subtitles to the video (see https://www.bannerbear.com/blog/how-to-add-subtitles-to-a-video-file-using-ffmpeg/)
- don't output the lyrics anymore, just the video is enough
- store the video in the persons memory
# CLI
Show CLI information (2)
# cli()
| Input | | |
| ---------- | -- | -- |
| - | | |
| **Output** | | |
## 📄 cli (unexported const)
# Tests
Show test information(2)
# test()
| Input | | |
| ---------- | -- | -- |
| - | | |
| **Output** | | |
## 📄 test (unexported const)
# Internal
Show internal (2)
# translateLyrics()
If I make this and I can find a way to do this for under a cent per song, we can integrate with spotify playtlists (our youtube playlists, even easier) in order to create a way for people to much more easily learn a language through music.
Once AI improves further, we might be able to use voice to voice, and input the original lyrics + the translated variant, to output a translated version that flows the same... This would be truly amazing.
NB: Many of these steps are useful by themselves as plugins to, for example, open-ai.
| Input | | |
| ---------- | -- | -- |
| name | string | |,| artist | string | |,| targetLanguage | string | |
| **Output** | | |
## 📄 translateLyrics (exported const)
If I make this and I can find a way to do this for under a cent per song, we can integrate with spotify playtlists (our youtube playlists, even easier) in order to create a way for people to much more easily learn a language through music.
Once AI improves further, we might be able to use voice to voice, and input the original lyrics + the translated variant, to output a translated version that flows the same... This would be truly amazing.
NB: Many of these steps are useful by themselves as plugins to, for example, open-ai.