David Attenborough narrates your life
Go to file
Charlie Holtz 1174275b5b
Merge pull request #26 from gaborcselle/parametrize-voice-id
2023-11-18 11:10:18 -05:00
assets first commit 2023-11-07 10:27:35 -05:00
frames commit empty frames folder to save pictures 2023-11-15 22:44:40 +00:00
.gitignore commit empty frames folder to save pictures 2023-11-15 22:44:40 +00:00
README.md Parametrize voice ID via another environment variable. 2023-11-17 10:50:12 -08:00
capture.py Create frames directory if it doesn't exist 2023-11-15 13:54:16 -05:00
narrator.py Actually set Elevenlabs API key from environment variable 2023-11-17 12:30:59 -08:00
requirements.txt add missing dependencies to `requirements.txt` 2023-11-15 18:51:03 +01:00

README.md

David Attenborough narrates your life.

https://twitter.com/charliebholtz/status/1724815159590293764

Want to make your own AI app?

Check out Replicate. We make it easy to run machine learning models with an API.

Setup

Clone this repo, and setup and activate a virtualenv:

python3 -m pip install virtualenv
python3 -m virtualenv venv
source venv/bin/activate

Then, install the dependencies: pip install -r requirements.txt

Make a Replicate, OpenAI, and ElevenLabs account and set your tokens:

export OPENAI_API_KEY=<token>
export ELEVENLABS_API_KEY=<eleven-token>

Make a new voice in Eleven and get the voice id of that voice using their get voices API, or by clicking the flask icon next to the voice in the VoiceLab tab.

export ELEVENLABS_VOICE_ID=<voice-id>

Run it!

In on terminal, run the webcam capture:

python capture.py

In another terminal, run the narrator:

python narrator.py