Building a Sub-Second Voice Pipeline with On-Device STT
How we achieved sub-second time-to-first-audio by moving speech recognition on-device, eliminating cloud round-trip latency entirely.
From the Lab
Engineering & Research
Technical notes from the DeVed Labs applied research team.
All Posts
Multi-Layer Safety: Content Filtering for Children's Voice AI
A walkthrough of our multi-stage safety architecture : from real-time evaluation on device to server-side fallback triggers.
Character Voice Design for Kids
Designing the Memo companion character and the voice pipeline that brings its personality to life : warmth, pacing, and prosody that feels right for a child.
COPPA Compliance by Architecture, Not Afterthought
Built-in compliance through on-device processing and zero data monetization : privacy guarantees that can't be misconfigured away.
From Research to Production: Shipping Voice AI to Real Kids
Lessons learned moving from a promising demo to a production product that real children use daily : where the hard problems actually live.