https://github.com/tanmay-chandgude/transcripto
Blog Dashboard for seamless text and video content input, transcription, translation, and publishing in multiple languages. Features include AI-powered transcription, translation into multiple languages, dynamic SEO-optimized blog publishing, and server-side rendering for fast performance.
https://github.com/tanmay-chandgude/transcripto
blogs gemini-ai kinde-auth nextjs reactjs shadcn-ui supabase-db transcribe translation typescript
Last synced: about 2 months ago
JSON representation
Blog Dashboard for seamless text and video content input, transcription, translation, and publishing in multiple languages. Features include AI-powered transcription, translation into multiple languages, dynamic SEO-optimized blog publishing, and server-side rendering for fast performance.
- Host: GitHub
- URL: https://github.com/tanmay-chandgude/transcripto
- Owner: Tanmay-Chandgude
- Created: 2025-02-06T13:44:15.000Z (3 months ago)
- Default Branch: main
- Last Pushed: 2025-02-25T17:32:21.000Z (3 months ago)
- Last Synced: 2025-02-25T18:35:27.722Z (3 months ago)
- Topics: blogs, gemini-ai, kinde-auth, nextjs, reactjs, shadcn-ui, supabase-db, transcribe, translation, typescript
- Language: TypeScript
- Homepage:
- Size: 3.58 MB
- Stars: 0
- Watchers: 1
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Transcripto
A modern web application for transcribing and translating audio/video content using AI.
## Features
- **Transcription**
- Support for audio and video files (mp3, wav, m4a, ogg, mp4, webm, mov, avi)
- File size limits: 10MB (free) / 25MB (pro)
- Real-time transcription using OpenAI Whisper
- **Translation**
- Support for 22 Indian languages
- Major global languages included
- Powered by Google's Gemini AI
- Document translation (.txt, .doc, .docx, .pdf)
- Direct text input support
## Tech Stack
- Next.js 14 (App Router)
- TypeScript
- Tailwind CSS
- OpenAI Whisper API
- Google Gemini AI
- Supabase
- Kinde Auth
A modern web application for transcribing and translating audio/video content using AI.
## Features
- **Transcription**
- Support for audio and video files (mp3, wav, m4a, ogg, mp4, webm, mov, avi)
- File size limits: 10MB (free) / 25MB (pro)
- Real-time transcription using OpenAI Whisper
- **Translation**
- Support for 22 Indian languages
- Major global languages included
- Powered by Google's Gemini AI
- Document translation (.txt, .doc, .docx, .pdf)
- Direct text input support
## Tech Stack
- Next.js 14 (App Router)
- TypeScript
- Tailwind CSS
- OpenAI Whisper API
- Google Gemini AI
- Supabase
- Kinde Auth
## Getting Started
1. Clone the repository
2. Install dependencies:
```
3. Set up environment variables in `.env.local`:
NEXT_PUBLIC_SUPABASE_URL=your_supabase_url
NEXT_PUBLIC_SUPABASE_ANON_KEY=your_supabase_key
KINDE_CLIENT_ID=your_kinde_client_id
KINDE_CLIENT_SECRET=your_kinde_secret
KINDE_ISSUER_URL=your_kinde_issuer
NEXT_PUBLIC_GEMINI_API_KEY=your_gemini_key
OPENAI_API_KEY=your_openai_key
```
4. Run the development server:
```bash
npm run dev
```
## License
MIT
```
## License
MIT