Add some sanity to your reading workload. Make neural network sythesized audiobooks from text files.
Key Features • Install • Develop • Examples • Contributing • Todo • License
- AWS Polly and Google Text to Speech Support
- Note: AWS Polly support coming soon
- Simple command line interface
mkab synth reading.txt -o reading.ogg
- Fast! Uses concurrent requests to sythesize audio
- Note: Feature under construction
- Python 3
- Google Cloud API Key
- AWS API Key (client_id and secret)
Install from source
The following commands install adds mkab to your $PATH
git clone https://github.com/grplyler/mkab.git
cd mkab
python setup.py install
git clone https://github.com/grplyler/nginup.git
cd nginup
python setup.py develop
Coming soon
I created this tools to handle the ridiculous amount of reading I had in college. As a pretty good auditory learner with pretty bad dyslexia, it really helped! And in most cases, I felt like my comprehension was much better.
If you like this project, here are some ways you can contribute!
- Feature Requests
- Bug Reports
- Platform Testing
- [] Add support for AWS Polly
- [] Add more convenient way to manage API config
- [] Add support for ssml for more control of voicing synthesis
- [] Add additional features to the command line interface
- [] Add more advanced text sanitization algorithms
- [] Create a web interface
- [] Deploy as a service there users can buy tokens that let them generate audiobooks instead of having to have an AWS or GCP API key
MIT