AI-powered platform that improves communication skills, offering real-time feedback for public speaking, debates, and conversations.
SpeechViber is an innovative AI-powered communication training platform that helps users improve their public speaking, debate, and conversation skills. Using advanced speech recognition and AI analysis, it provides real-time feedback on tone, pace, clarity, filler words, and overall delivery.
What makes it unique:
- Real-time speech analysis
- AI-powered feedback on delivery
- Multiple practice modes (public speaking, debates, conversations)
- Progress tracking over time
- Personalized improvement suggestions
- Real-time Analysis – Instant feedback on your speech
- Filler Word Detection – Identify and reduce "um", "uh", "like"
- Pace & Tone Analysis – Optimize speaking speed and vocal variety
- Clarity Scoring – Measure articulation and pronunciation
- Practice Modes – Public speaking, debates, casual conversations
- Progress Tracking – Monitor improvement over time
- Recording Playback – Review and analyze past sessions
Frontend
- JavaScript
- React
- HTML/CSS
AI / ML
- Web Speech API
- Speech Recognition
- Natural Language Processing
Audio Processing
- Web Audio API
- Audio visualization
Deployment
- GitHub Pages
Microphone Input → Speech Recognition → AI Analysis → Feedback Generation → Visual Display → Progress Storage
# Clone the repository
git clone https://github.com/DevRanbir/speechviber.git
# Navigate to project
cd speechviber
# Install dependencies
npm install
# Start development server
npm startCreate a .env file and add:
REACT_APP_SPEECH_API_KEY=your_speech_api_key
REACT_APP_AI_FEEDBACK_KEY=your_ai_api_key- Step 1: Allow microphone access
- Step 2: Select practice mode (speech, debate, conversation)
- Step 3: Start speaking
- Step 4: Receive real-time feedback
- Step 5: Review analysis and improve
- Live Demo: https://devranbir.github.io/speechviber/
speechviber/
├── src/
│ ├── components/
│ │ ├── SpeechRecorder.js
│ │ ├── FeedbackDisplay.js
│ │ └── ProgressTracker.js
│ ├── services/
│ │ ├── speechAnalysis.js
│ │ └── audioProcessing.js
│ └── App.js
├── public/
└── README.md
- Add emotion detection in speech
- Implement accent training
- Create group practice sessions
- Add AI conversation partner
- Implement video analysis for body language
- Name: DevRanbir
- GitHub: https://github.com/DevRanbir
This project is licensed under the MIT License.
