Skip to main content
AiSlackin
HomePosts

Ai

slug-tts-stt: giving a mini-PC ears and a mouth, on two different chips

slug-tts-stt: giving a mini-PC ears and a mouth, on two different chips

2026-08-06 ·2 min read

Speech-to-text on the XDNA2 NPU and text-to-speech on the Radeon iGPU of one Ryzen AI box — split across accelerators so they never contend, measured and reboot-verified.

amdnputtssttself-hostedai
quill-of-hermes: LAN OCR that eats PDFs and multi-page TIFFs

quill-of-hermes: LAN OCR that eats PDFs and multi-page TIFFs

2026-07-30 ·2 min read

A LAN web service wrapping OvisOCR2 GGUF and llama.cpp — images, PDFs up to 50 pages, and multi-page TIFFs in, Markdown out, with a Hermes skill on top.

ocrhermesllama-cppself-hostedai

Recent Posts

  • hed: the tiny C++ editor that replaces heredocs and makes agents happy 2026-09-27
  • MoACubed: teaching Hermes which profiles actually work 2026-09-06
  • Argus: the intel agent sheds its cron plumbing 2026-08-27
  • npu-monitor: a system tray that knows what hardware each box actually has 2026-08-21
  • hermes-shortcut-cheat-sheet: the shortcut list from source, not docs 2026-08-19

Tags

agents ai ai-agents amd android argus automation benchmarks cli code-review cost cpp csv cuda databases documentation editor evaluation extension file-transfer firefox github gpu hed hermes homelab javascript kde keyboard-shortcuts linux llama-cpp memory moa monitoring npu nvidia ocr open-source p2p postgres profiles proxmox python research rocm security self-hosted skills stt supply-chain tooling tts ux virtualization workflow

Archive

  • 2026 3

Follow Me

GitHub Medium RSS

© 2026 AiSlackin.

Powered by Hugo Primer Blog