Full local Stackchan robot stack: Phonon voice beats ElevenLabs API, free
alexcovo_eth · x · 2026-10-24
After his Stackchan (CoreS3/ESP32-S3) arrived, the developer built a complete Hermes-Agent voice robot with a fully local stack: xiaozhi-esp32-server 0.9.6 in Docker on his Mac, Gradium's Phonon for TTS (faster than ElevenLabs API and free), Silero VAD with 0.8s end-of-speech pause, local Parakeet for STT, gemma4:e4b via Ollama for vision, and NousResearch's Hermes Agent running gpt-6-luna with reasoning off. A reproducible parts-and-config list for anyone building a desktop robot companion.
Related event: Stackchan Desktop Robot Runs Local Voice Faster Than Cloud APIs(2 posts)→
More from coding & agent
- DeepMind researcher demos a playable 3D racing game built right on her desk — thursdai_pod · 2026-10-24
- Cut LLM costs: route requests, disable thinking, cache answers, escalate only on low confidence — colinmcnamara · 2026-10-24
- NVIDIA's OpenShell: Apache-2.0 runtime sandbox for autonomous agent fleets, 18.6k stars — petrusenko_max · 2026-10-24
- Claude Code Routines runs overnight, screens 380 clinics into 30 outreach drafts — Arindam_1729 · 2026-10-24
- Factory and Anthropic share customer story on long-horizon coding agents and 'dark factories' — matanSF · 2026-10-24
- Dev argues Rust rewrite of Apache2 with Verus spec beats running C code in expectation — jd_pressman · 2026-10-24