GitHub - aTrapDeer/Comedian-TimDillon-img2Audio: Translate any image to a comedian (Tim Dillon) podcast script using HuggingFace, OpenAI and ElevenLabs. You must create your own voice model of comedian and use your own api keys. Reference the sample DotEnv file to input your own keys. This saves almost all of the work for you though coding wise.

aTrapDeer / Comedian-TimDillon-img2Audio Public

Notifications You must be signed in to change notification settings
Fork 0
Star 0

Translate any image to a comedian (Tim Dillon) podcast script using HuggingFace, OpenAI and ElevenLabs. You must create your own voice model of comedian and use your own api keys. Reference the sample DotEnv file to input your own keys. This saves almost all of the work for you though coding wise.

0 stars 0 forks Branches Tags Activity

Star

Notifications

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 6 Commits
Aptfile		Aptfile
DOTENV-SAMPLE.TXT		DOTENV-SAMPLE.TXT
Procfile		Procfile
main.py		main.py
requirements.txt		requirements.txt
setup.sh		setup.sh