Inspiration
Our Project is built on a core idea that takes an audio file as an input and generates a video file
What it does
It converts any audio file to video.
How we built it
Using Python, Assembly AI, and Open AI
Challenges we ran into
Programming to get the essence of sentence by using the grammar rules
Accomplishments that we're proud of
The automation level we achieved. The only manual intervention we did was to create a dataset.Rest all the code was able to figure out , selecting required images , sentences generation and video generation. We are proud especially for algorithm we built , to extract out the dialogues from the sentences and build subtitles data out of it.
What we learned
API requests , NLP using spacY
What's next for Audio to video generator with content recognition
There is a few latency issues, which should be fixed.Also next time , we plan to automate the generation of images either webscraping or using AI.Also enhance images by considering adjectives while searching for images
Built With
- assemblyai
- natural-language-processing
- openai
- python
Log in or sign up for Devpost to join the conversation.