I'm using this app to create videos using ffmpeg from audio recordings I make for my Cantonese language learning Instagram: https://instagram.com/meglearnscanto

Try out the app here: https://mrisdal-canto-podcast-creator-create-podcast-oselu7.streamlit.app/

1. Upload an audio file (m4a format)
2. Choose a background (an image that lives in ./input/backgrounds/)
3. Download the result (a video of the image with an audio waveform overlaid)

The images were pre-generated using diffusion models on Hugging Face.

Here's an example of what the end result looks like