tinker-sound-effect
A local text-to-sound-effect plugin for TINKER, powered by audio.cpp via audiocpp-static.

Features
- Local SFX generation with Stable Audio 3 Small SFX (Q8 / F16 GGUF)
- English text prompts with optional negative prompt
- Duration control (1–30s) for each generation
- Auto model download via Downloader into
~/.tinker/models/when missing - Generation queue with WaveSurfer preview, play, and save as WAV
Installation
Download and install TINKER, then run:
bash
npm i -g tinker-sound-effectUsage
- Describe a sound in English (e.g. “A wooden door creaks open slowly in a quiet hallway”)
- Optionally set a negative prompt, duration, model, and download source
- Click Generate — missing models start downloading automatically
- Preview queued results in the audio list; save WAV when ready
Prompts work best in English. Runtime data lives in ~/.tinker/tinker-sound-effect/ (logs / outputs). Models are shared under ~/.tinker/models/.