Building a bilingual Stack-chan desktop bot with local LFM-3-Audio
alexcovo_eth · x · 2026-11-22
Replying to mongonta555's bilingual Stack-chan, the author shows his own version powered by a locally-running Liquid AI LFM-3-Audio model that speaks both English and Japanese — a DIY combo of on-device audio models and a desktop robot.
Related event: Makers Build Bilingual Stack-chan Robots with Local AI Models(2 posts)→
More from Embodied
- Tesla's overhead parking view is generated video, not stitched camera feeds — PTrubey · 2026-11-22
- Frontier LLMs solved robot in-context learning as a side effect, says researcher — YouJiacheng · 2026-11-22
- PhD intern's trick: carbon fiber TPU turns a Fin-Ray gripper into its own touch sensor via flex-dependent resistance — burhop · 2026-11-22
- Gemini 4 Neon builds an interactive 3D neural character demo, no NVIDIA GPU needed — Eric520CC · 2026-11-22
- Tesla FSD V14 safety debate: Musk says 2-3x safer than humans, Douma argues closer to 10x — jamesdouma · 2026-11-22
- Neon agent turns photos into Blender 3D models via colmap in one hour — eigenhector · 2026-11-22