A voice assistant that holds the thread of a conversation

The problem

Building a voice AI application that feels genuinely natural requires solving multiple challenges simultaneously: accurate speech recognition across accents and noise environments, real-time natural language understanding, contextually relevant response generation, and a mobile UX that makes AI interaction feel effortless. Our team fine-tuned the speech recognition pipeline to handle varied accents and background noise with high accuracy. The conversational AI engine maintains context across multi-turn interactions — remembering previous parts of a conversation to generate coherent, relevant responses. Response latency was a critical focus: we optimised the AI inference pipeline to deliver sub-second responses, making conversations feel natural rather than transactional. The voice UI was designed with accessibility in mind, ensuring the experience works for users of all backgrounds and technical comfort levels.

What we built

• Speech recognition tuned for varied accents and background noise rather than for a quiet room.
• A conversational engine that keeps context across multi-turn exchanges, so a follow-up can just be a follow-up.
• Response generation over LLM models instead of a fixed set of intents.
• Multilingual input, so people can speak in the language they think in.
• An Android app designed around voice as the primary interface, not as an add-on to a keyboard.

What made it hard

Four problems have to be solved simultaneously before any one of them counts: recognition that survives accents and noise, understanding that happens in real time, responses that are actually relevant to what was asked, and a mobile experience where talking to it is genuinely easier than typing. Get three right and the fourth still sinks it.

How we built it

• Fine-tuned the recognition pipeline against varied accents and noisy environments.
• Carried conversational context across turns, so earlier parts of an exchange inform later ones.
• Optimised the inference pipeline for sub-second responses — latency is what makes a conversation feel transactional.
• Designed the voice interface for accessibility, so it works across technical comfort levels rather than assuming a power user.

Who it is for

Android users who want assistance by speaking — hands busy, screen out of reach, or simply faster out loud — including people for whom typing is the barrier rather than the convenience.