Phonon TTS pipeline ported to GenieX, targeting on-device NPU inference
HowDevelop · x · 2026-10-21
A developer shared a collaboration with @carrycooldude, @ashwinexe and @BhosalePratim bringing the Phonon TTS pipeline to GenieX, targeting NPU hardware. The attached photo shows a smart-mirror demo rig built on a dev board — an early attempt at running speech synthesis fully on-device. Details remain thin.
More from Embodied
- ZJU's VLA-Rolling reuses discarded action tails to cut VLA inference cost across 16 model-benchmark pairs — OmniAI-ZJU · 2026-10-21
- Maker 3D-prints an adapter to mount a chuck onto a robot motor — _Stocko_ · 2026-10-21
- Ropedia releases open W0 world model trained on 10,000 hours of egocentric human video — liuziwei7 · 2026-10-21
- Characterizing a cheap SG90 servo with Claude's plan to build a MuJoCo model — _Stocko_ · 2026-10-21
- Berkeley researchers introduce Advantage Guidance, an RL recipe for VLAs hitting ~70% success — berkeley_ai · 2026-10-21
- The New Yorker: We're Learning to Live With Waymos, and It's Going Weird — njrc · 2026-10-21