AI That Urges You to Unplug: Pranav Suryawanshi Unveils TouchCall Voice Assistant for the Hacktoberfest AI Challenge

In an era where digital wellness applications often paradoxically demand more of our screen time to monitor our health, a new open-source project is attempting to flip the script. Developed by Pranav Suryawanshi, "TouchCall" is a voice-first AI assistant designed with a singular, counter-intuitive goal: to use the power of artificial intelligence to encourage users to put their phones down and engage with the physical world.

The project was recently introduced as a submission for the Hacktoberfest Open-Source AI Challenge, specifically addressing the "Touch Grass" theme of the competition’s first week. By moving away from traditional graphical user interfaces and toward a seamless voice-only interaction model, Suryawanshi aims to solve a persistent problem in the productivity and wellness space—the "notification trap" that keeps users tethered to their devices even when they are trying to disconnect.

The Vision Behind TouchCall: Technology as a Bridge to the Real World

The philosophy driving TouchCall is rooted in the observation that most modern technology is designed for maximum "stickiness." From social media feeds to productivity suites, the goal is often to keep the user’s eyes on the glass. Even wellness apps, which are intended to help users relax or exercise, frequently require them to navigate complex menus, log data manually, and respond to pings, thereby increasing overall screen time.

Suryawanshi’s approach suggests that technology should sometimes serve as a reason to step away from technology. TouchCall functions as a conversational partner that encourages outdoor activities, such as taking a walk or exercising, through natural dialogue. By utilizing voice interaction, the assistant removes the need for visual engagement, allowing the user to keep their phone in their pocket or across the room while they prepare to head outside.

The developer describes TouchCall as a lightweight, open-source initiative. The core mission is to create an AI that acts as a nudge toward the physical environment, rather than a vacuum for digital attention. In his project documentation, Suryawanshi emphasizes that the assistant is built to be a voice-first experience, ensuring that the transition from a digital task to a real-world activity is as frictionless as possible.

A Functional Prototype: Demonstrating the Voice Pipeline

While still in the prototype stage, TouchCall—which is also hosted on GitHub under the repository name "OutVoice"—demonstrates a sophisticated and functional voice processing pipeline. The project currently exists as a local implementation that proves the feasibility of a fully open-source, voice-operated AI assistant.

The current iteration of the system allows a user to speak to the assistant, which then processes the speech, generates a contextually relevant response using a Large Language Model (LLM), and speaks back to the user. This "round-trip" interaction is the foundation of the TouchCall experience. Unlike many commercial voice assistants that rely heavily on cloud-based processing and proprietary algorithms, Suryawanshi’s prototype is built to run locally, ensuring that the interaction is both private and customizable.