Initial commit — voice pipeline experiment

STT (Silero VAD + Whisper via sherpa-onnx), Chatterbox TTS HTTP server,
query completeness classifier (Ollama), multi-voice demo scripts, and
planning docs. Kept as reference; clean rewrite planned in separate repos.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

LLM-ROUTING.md

@@ -0,0 +1,51 @@
+# LLM Routing Strategy
+
+When to use a local model vs an Anthropic frontier model in the voice pipeline.
+
+---
+
+## Current model inventory
+
+| Role | Model | Where | VRAM |
+|------|-------|-------|------|
+| STT | Whisper base.en + Silero VAD | sherpa-onnx (GPU) | ~0.5 GB |
+| TTS | Chatterbox Turbo | Python/CUDA | ~4 GB |
+| Completeness classifier | Qwen 2.5 3B | Ollama | ~2 GB |
+| Main reasoning | Claude (Anthropic) | API / Claude Code | — |
+
+Total local VRAM: ~6–7 GB on RTX 3090 (24 GB). Plenty of headroom.
+
+---
+
+## Routing principles
+
+### Use local model when:
+- Task is **classification or routing** (completeness, intent detection, command vs question)
+- Task is **latency-sensitive** and the answer doesn't require world knowledge or reasoning
+- Task is **high-frequency** (runs on every utterance — billing would add up)
+- Privacy matters — query content shouldn't leave the machine
+
+### Use Anthropic frontier model when:
+- Task requires **reasoning, synthesis, or judgment**
+- Task involves **code generation or editing**
+- Task involves **world knowledge** beyond what a small model handles well
+- Query is **low-frequency** (once per user request, not once per audio frame)
+- Quality matters more than latency
+
+---
+
+## GPU split (future option)
+
+If voice models and reasoning models compete for VRAM, split across cards:
+- **Card A** (smaller VRAM): STT + TTS + classifier — pure inference, no large models needed
+- **Card B** (larger VRAM): local reasoning model (e.g. Qwen 20B or similar) for tasks that benefit from a capable local model but shouldn't hit the API
+
+Use `CUDA_VISIBLE_DEVICES` or Ollama's GPU assignment to pin models to specific cards.
+
+---
+
+## Upgrade candidates
+
+- **Whisper small.en or medium.en** — better transcription accuracy, especially for accents. Small adds ~0.5 GB, medium ~1.5 GB.
+- **Completeness classifier → larger model** — Qwen 7B or 14B would give significantly better sentence boundary detection and instruction/question classification.
+- **Local reasoning model** — for tasks that are too simple to warrant an API call but too complex for a 3B classifier (e.g. summarisation, note-taking, simple Q&A). A 7–14B quantised model via Ollama would fit alongside the voice stack.