
GCP
Utilizing Vision API and TTS to synthesize audio out of images.
Learn moreREADME is more than just accessible, it's a no-hand life-changer. Using a mini-camera attached to one's glasses, README retrieves text from an image and synthesizes an audio file that reads the text outloud for the person. Any text, handwritten or printed, can be read out loud, whether it be through the click of the button or voice activation.
Learn moreUsing the document text detection feature under GCP Vision API, we retrieve text data from an uploaded base64 image in a JSON format.
Learn moreThe text data is then sent over to GCP TTS, and the service synthesizes a base64 audio file. The pipeline of the GCP APIs is written in Golang and is served on Google Cloud App Engine as a REST API.
Learn moreREADME's technology empowers the blind to live better lives.
Utilizing Vision API and TTS to synthesize audio out of images.
Learn moreSimplifying the hosting process.
Learn moreConsuming the backend REST API.
Learn moreCreating a pipeline REST API for GCP.
Learn more