https://github.com/stefanangelovski/voice_to_tweet

Tweet with your Voice using Whisper STT from OpenAI and Twitter4J flow to connect and talk with any account.
https://github.com/stefanangelovski/voice_to_tweet

ai frontend openai twitter website whisper x

Last synced: about 1 month ago
JSON representation

Tweet with your Voice using Whisper STT from OpenAI and Twitter4J flow to connect and talk with any account.

• Host: GitHub
• URL: https://github.com/stefanangelovski/voice_to_tweet
• Owner: StefanAngelovski
• Created: 2024-08-21T11:55:45.000Z (5 months ago)
• Default Branch: main
• Last Pushed: 2024-10-26T23:13:16.000Z (3 months ago)
• Last Synced: 2024-11-03T23:43:45.204Z (3 months ago)
• Topics: ai, frontend, openai, twitter, website, whisper, x
• Language: Java
• Homepage: https://voicetotweet.physdev.site/
• Size: 35.2 KB
• Stars: 0
• Watchers: 1
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Voice To Tweet

![VoiceToTweet](https://github.com/user-attachments/assets/e11859d7-4522-49a1-add2-38beb844672d)

**Voice To Tweet** is a web-based application that transcribes spoken words into text using OpenAI's Whisper Speech-to-Text model. The transcribed text is then posted as a tweet on X (formerly Twitter) via the Twitter4J API.

### Technologies

- **OpenAI Whisper**: Converts speech to text.

- **Twitter4J**: Posts tweets to X (Twitter).

- **JavaScript**: Captures microphone input as a `.wav` file and handles front-end logic.

- **Spring Boot**: Powers the back-end server.

- **Thymeleaf**: Template engine for rendering HTML.

### How It Works

1. The user records speech via the web interface.

2. JavaScript converts the microphone input into a `.wav` file.

3. The `.wav` file is sent to Whisper, which transcribes the speech into text.

4. The transcribed text is posted to X using the Twitter4J API.

The back-end is built using **Spring Boot**, with **Thymeleaf** for rendering the front-end. **JavaScript** handles the front-end logic, particularly converting the audio and sending it to the back-end.

This project was created for the **Web Programming** course at the **Faculty of Computer Science and Engineering**, Skopje.

You can check the website out [here](https://voicetotweet.physdev.site).

---