Chorus AI app for Lablab AI Hackathon - GPT-4o Challenge
Watch the video below to understand how the Speech Impairment Advisor works:
The Chorus AI app is an AI-based voice application designed to assist users in improving their voice quality. It is particularly useful for individuals experiencing voice disorders or speech impairments that affect their communication ability. The app provides voice feedback, improvement advice, and exercise demonstrations tailored to the user's needs.
- Voice Feedback: Analyzes and provides feedback on the user's voice quality, noting any abnormalities or areas for improvement.
- Voice Improvement Advice: Offers specific advice and strategies to enhance voice quality, including techniques to correct tone, pitch, and tempo.
- Exercise Demonstrations: Provides practical exercises designed to improve speech and voice issues, ensuring these exercises are clear and actionable.
- OpenAI GPT-4o: For generating responses.
- Whisper: For audio transcription.
- Sounddevice and Soundfile: For audio handling.
- Playsound: For audio playback.
- Record Audio: The app listens for user speech, records the audio, and transcribes it into text.
- Generate Response: The transcribed text and relevant context are sent to the GPT-4o model to generate a response.
- Text-to-Speech: The generated response is converted to speech and played back to the user.
We welcome contributions to enhance the Speech Impairment Advisor. Please fork the repository and submit pull requests.
This project is licensed under the MIT License.