transaudio
TransAudio is a web app designed to simplify speech-to-text conversion using cutting-edge technologies and AssemblyAI’s advanced speech recognition capabilities for audio data that doesn’t need double checking. Turn that audio disaster into a readable mess.
- Timeline: Started July 2024
- Technologies: Next.js, React, Tailwind CSS
Features 🧩
- MP3 Transcription
- Real-time Progress Tracking
- Speaker Diarization
- Speaker Labeling
- Automatic punctuation and casing
- Filler words and Profanity Filtering
How It Works 🛠️
Here’s a quick rundown of how it works:
User Uploads MP3, or drags and drops it
⇣
Upload starts
⇣
Transcription Initiated
⇣
Transcription Completed
⇣
Display Transcript, Confidence Score and Backend Run Time
After the transcription is completed, the user is presented with the transcript and its confidence score. The user can either download the transcript or copy it to the clipboard. Or even reset the process to upload a new file.
Performance Metrics 📊
| Metric | Value |
|---|---|
| Average Run Time | 30-60 seconds |
| Maximum File Size | Up to 10 MB |
| Supported Audio Format | MP3 |
| Browser Compatibility | Chrome, Firefox, Safari |
The uploaded audio files are not stored on the server. They are deleted after the transcription is completed. However, a json file is saved to the server for 30 days to keep track of the transcription request.
Design and Structure 🧰
The project is built using Next.js, React, Tailwind CSS.
transaudio
├── .next
├── public
├── src
│ ├── app
│ | ├── api
│ | ├── components
│ | ├── providers
│ | ├── styles
│ | ├── layout.tsx
│ | └── page.tsx
│ ├── lib
│ ├── types
│ └── utils
├── package.json
├── tailwind.config.ts
├── tsconfig.json
└── next.config.ts
Future Roadmap 🛣️
- Support for additional audio formats (WAV, M4A)
- Advanced editing capabilities for transcripts
- Integration with cloud storage platforms
- Multi-language transcription support
- File size limit increase
Skills Gained 💪
- Frontend Development
- UI/UX Design
- Performance Optimization
- API Integration
- File Handling
Live Demo 🌐
Check out the live demo at transaudio.geltaverse.com.
If you want to chat about this project or anything else, email me at hello@geltaverse.com.
Thanks for reading!