DEV Community

Cover image for VocalScribe: Transform Your Audio Into Text with Precision
ANIRUDDHA
ANIRUDDHA

Posted on

VocalScribe: Transform Your Audio Into Text with Precision

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

What I Built

🛠️ I built VocalScribe, a modern web application that allows users to transcribe recorded audio into text. Using AssemblyAI's Speech-to-Text API, the app can transcribe audio from uploaded files, such as .mp3, into accurate text.

🎤 VocalScribe features a variety of functionalities designed for an interactive and seamless transcription experience:

  • 📝 Users can upload .mp3 files for transcription.
  • ⏱️ The app generates real-time transcriptions from the uploaded audio files.
  • 📋 Users can copy, download, delete, and share the transcriptions to social media platforms like Facebook, Twitter, and LinkedIn.
  • ❤️ The app supports interactive features such as liking, commenting, and editing transcripts.
  • 🌙 The app also includes a dark/light mode toggle for enhanced visual comfort and animated transitions for a more engaging experience.

💻 Built using React, TypeScript, and Tailwind CSS, VocalScribe offers a modern and responsive design that works seamlessly across devices.

Demo

🔗 You can try the app here (vercel):VocalScribe Demo

😺 Github Repository :code

Screenshots:
Screenshot 1
User Interface with dark/light mode toggle.

Screenshot 2
App’s clean and responsive design.

Image description

Image description

Journey

🧠 Universal-2, AssemblyAI’s powerful Speech-to-Text model, powers the VocalScribe transcription service. By integrating the AssemblyAI API, I was able to provide accurate transcriptions from recorded audio files, such as .mp3. The transcription process happens after the file is uploaded and processed, ensuring precise results.

Key Steps in the Integration:

  1. 📤 Audio File Upload: Users upload an .mp3 file, which is sent to AssemblyAI’s API for transcription.
  2. Transcription Process: The uploaded file is processed by AssemblyAI’s model, and the transcription appears with timestamps.
  3. 🔄 Additional Features:
    • ✂️ Users can copy, edit, or delete their transcript.
    • 👍 They can like or comment on transcripts to increase interaction.
    • 🔗 Share transcripts to social media platforms for easy distribution.

Conclusion

VocalScribe effectively showcases the power of AssemblyAI’s Universal-2 Speech-to-Text Model for transforming recorded audio files into accurate transcriptions. By adding features like file upload, transcript editing, commenting, and social media sharing, I’ve created a highly interactive platform for transcribing and interacting with audio content.

🙌 I truly appreciate the opportunity to build this project and look forward to hearing your feedback!

Thanks for reading!

Top comments (1)

Collapse
 
kiran_baliga profile image
Kiran Baliga

Nice!