Tech

The Web Speech API + Gemini + VOICEVOX setup is complete — an AI character you can actually have a voice conversation with. Key implementation notes and impressions.

Implemented all 12 text processing tools planned in the previous article. Also reorganized the category system and switched the listing UI to a table layout.

Design patterns for reducing context usage and API calls in the AI auto-dev loop: blocking waits, read-forbidden files, and session isolation.

I compiled research findings and implementation specifications for adding text-processing tools to lilting.ch/lab. Based on a comparison with DevToys, it highlights the gaps and documents detailed specs for 12 candidate tools.

A comparison of major AI 3D generation tools such as TRELLIS, Hunyuan 3D, Tripo AI, and Hitem3D, with a focus on image requirements for better 3D output.

Setup notes for Qwen-Image-Edit-2511 on RunPod's RTX 4090 ($0.34/hr) using the ComfyUI template. Includes the fal Multiple-Angles LoRA (4 elevations × 8 azimuths × 3 distances) and a per-image cost breakdown that ends up cheaper than buying a 4090.

I looked into whether I could build my own macOS SFTP client with Tauri. Conclusion: yes, absolutely.

Open-source TTS with 100M parameters that runs faster than real time on CPU. Supports voice cloning.

Running the Claude Code + Codex auto-loop for real. Generated 1,134 lines of game code.

Use gh-setup-hooks to install the GitHub CLI automatically and complete the whole flow, from branch merge to Vercel deploy, directly in the web environment.

Technical prep for automating an implement → review → fix loop with Claude Code and OpenAI Codex via tmux. Can it build something overnight unattended?

VRAM per quantization for the 20B Qwen-Image-Edit-2511 in one table: FP8 from 6GB, NF4 16–20GB, BF16 24GB+, GGUF Q4 CPU-runnable. Minimum RTX 3060 12GB and recommended RTX 4070 Ti 16GB builds, plus the 96-angle Multi-Angle LoRA.