Face Resonance

Face resonance capture your face and analyse it, and create bespoke voices for you!

Inspiration

Frustrated by generic AI voices that don't represent diverse identities - we wanted voices that match your age, gender, background, mimics, facial phenotype features and emotions using cutting-edge AI technology.

What it does

Analyzes your face to generate personalized voices using ElevenLabs' revolutionary Voice Designer API - the latest breakthrough in AI voice synthesis. Our app tailors tone, accent, and characteristics to match your demographics and emotional state with unprecedented accuracy.

How we built it

Built with React Native frontend, Python backend for face analysis, and integrated ElevenLabs' brand-new Voice Designer API - leveraging their most advanced voice generation model. We implemented custom ML models for facial analysis to feed into ElevenLabs' most recent voice design engine.

Challenges we ran into

Accurate demographic detection from facial features, optimising integration with ElevenLabs' newest Voice Designer features, real-time voice synthesis latency, and balancing personalisation with ethical AI usage.

Accomplishments that we're proud of

Created the first voice AI that combines facial analysis with ElevenLabs' groundbreaking Voice Designer technology, considering cultural identity and emotional context while achieving high accuracy in demographic-matched voice generation using the most advanced AI voice models available.

What we learned

Importance of inclusive AI design, the incredible potential of ElevenLabs' Voice Designer for personalized applications, technical complexity of real-time voice synthesis, and the need for responsible AI guidelines in voice technology.

What's next for Face Resonance

Expanding integration with ElevenLabs' latest Voice Design api features, adding more language support, improving emotion detection accuracy, implementing voice cloning safeguards, and exploring accessibility applications for speech disabilities.