Freelancer Transcription Tool - Transform Audio to Text with AssemblyAI 🚀

This is a submission for the AssemblyAI Challenge : Sophisticated Speech-to-Text.

What I Built

The Freelancer Transcription Tool is a cutting-edge, user-friendly application designed to enhance productivity by converting audio into accurate, timestamped text. Built during the AssemblyAI Challenge, this tool demonstrates innovation in audio-to-text technology and provides features that cater to freelancers, researchers, and content creators.

Demo

Live Demo 🎉

GitHub Link

GiTHub

Journey

Participating in the AssemblyAI Challenge, I aimed to create a tool that not only transcribes audio but also provides real-time sentiment analysis, speaker labeling, and export options. By leveraging AssemblyAI’s Universal-2 Speech-to-Text model, I was able to incorporate powerful transcription and analysis features seamlessly.

Key Features:

1. File Upload & Playback:
   Drag-and-drop or file picker for easy audio uploads.
   Smooth progress bar indicating upload status.
   Local audio playback with intuitive controls.

2. Transcription with Timestamps:
   Generate transcription with optional timestamps.
   Real-time manual timestamp addition and clickable timestamps.

3. Search Functionality:
   Search specific words in the transcription, with results highlighted dynamically.

4. Export Options:
   Export transcription as .TXT or .PDF, with or without timestamps.

5. Sentiment Analysis:
   Analyze sentiment (Positive, Neutral, Negative) at the sentence level.

6. Speaker Labeling:
   Differentiate speakers with AssemblyAI’s speaker labeling feature.

7. Enhanced UI/UX:
   Fully responsive design with dark mode toggle.
   Real-time playback highlighting synced with transcription.

8. Editable Transcription:
   Edit transcriptions directly in the UI, with the option to remove timestamps.

Team :

It’s just me. A one-person army.

Project Image :