Easy Talk – Empowering Seamless Communication for People Who Stutter
The Problem: For individuals who stutter, verbal communication, particularly on phone calls, can be a source of anxiety and challenge. Whether it’s responding quickly or articulating words smoothly, the pressure of real-time conversation can be overwhelming. This can lead to avoidance of calls, missed opportunities, and barriers to both personal and professional interactions.
Our Vision: Our goal is to create Easy Talk, a mobile and web app designed specifically to help people who stutter feel more confident and comfortable during phone conversations. We want to provide a tool that enables them to express themselves without the fear of hesitation or interruptions, ensuring their voice is heard in a smooth, efficient way.
How It Works:
Automatic Call Handling: When a user receives a call, the app will intercept and answer the call on their behalf. During this time, the conversation will be transcribed in real-time using Speech-to-Text technology, allowing the user to follow the conversation comfortably.
Pre-Generated Responses: As the conversation unfolds, the app will generate a set of AI-powered suggested responses based on the context of the conversation. The user can then select one of these responses to communicate their message, which will be converted into speech using Text-to-Speech technology.
Voice Input Option: If the user feels confident in responding verbally, they can press a button to record their response, and the app will process their speech in a way that ensures smooth, clear communication with the other person on the call.
Custom Responses: The app also offers the ability for users to create and save custom responses that they can quickly select during calls. This is useful for frequently asked questions or responses that are used in professional environments, such as greetings or standard replies.
Core Features:
Real-Time Speech-to-Text Transcription: The app listens to the caller’s voice and displays it as text in real-time, allowing the user to read and understand the conversation at their own pace.
AI-Generated Responses: Three context-appropriate responses are generated using advanced language models. These allow the user to participate in the conversation without needing to speak immediately.
Text-to-Speech: Once the user selects their desired response, the app translates the text back into speech, enabling a smooth verbal interaction on their behalf.
User-Friendly Interface: The app features an intuitive interface where users can easily read, select, and manage their responses. The entire process from answering to responding is made seamless.
Customizable Responses: The app offers the flexibility of storing pre-written responses for regular communication needs, giving users full control over their interactions.
Technologies We Use:
- Google Speech-to-Text: Converts the caller’s voice into readable text for the user.
- Open AI-Powered Natural Language Processing: Generates three context-relevant responses based on the conversation.
- *Google Text-to-Speech *: Converts the selected response back into natural-sounding speech.
- React and Node.js: Power the frontend and backend for responsive, scalable performance across devices.
User Scenario:
Imagine a scenario where John, a young professional with a stutter, receives a call from his boss. Normally, John would feel a sense of panic, unsure of how to navigate the conversation smoothly. But with Easy Talk, John can accept the call through the app. As his boss speaks, John sees the words transcribed on his screen. The app suggests three potential responses, and John quickly selects the one that conveys his thoughts. The app converts his choice into clear speech, allowing him to respond effortlessly without stress. The result is a fluid, anxiety-free conversation.
Why Easy Talk?
Easy Talk is more than just a communication tool. It’s a bridge to confidence, ensuring that people who stutter can engage in conversations without feeling rushed, pressured, or judged. It’s a tool that gives them back their voice and helps them navigate daily communication challenges with ease.
Next Steps:
We are currently in the development phase, focusing on building the core features of real-time transcription, AI-generated responses, and TTS capabilities. Our roadmap includes adding more customization options, refining the user experience, and expanding accessibility features to make this tool universally beneficial to all people who stutter.
Log in or sign up for Devpost to join the conversation.