This is a submission for the AssemblyAI Challenge : Sophisticated Speech-to-Text.
What I Built
ChapTer2 AI is a web-based Speech-to-Text application that converts real-time spoken audio into text using advanced AI technology. Built with React, Bootstrap, and the AssemblyAI API, it offers a seamless and user-friendly experience for transcription, note-taking, and accessibility needs.
Demo
Journey
ChapTer2 AI uses AssemblyAI's real-time Speech-to-Text model, Universal-2, to convert spoken audio into text instantly. During the recording process, the app uploads the audio and requests the final transcription result from the API, ensuring the user only sees the complete and accurate text once the transcription is finished. This real-time approach simplifies the user experience, providing a clean and precise output without showing partial results.
As a beginner working with APIs and such challenges, I faced some difficulties with the integration, and the API didn’t work as expected at times. However, this project has been a great learning experience, and I look forward to enhancing it in the future.
i did this project alone
Top comments (0)