Built during the hackathon HawkHacks in May 2022.

SpeechFinder brings underheard voices to the center of a stronger public dialogue by allowing any user to contribute stories for civic action. They do so by uploading an audio file, which is run through AssemblyAI's API to extract keywords, phrases and entities, and transcribe the audio file.

Then journalists can search for stories in the database using keywords and even filter for local stories to recognize patterns over time and in-the-moment trends or discover unmet community needs worth investigating. The results provide keywords and audio transcript excerpts to give an idea of what the story is about. When clicking a result, journalists and other users can find a full audio transcript and use all of the information they find for many social purposes.

Built using React, Flask, Python and SQLite.