Generate Local Narration

Own script-to-WAV synthesis, pinned models/runtime, approved cache reuse and audio validation. tk-video owns scenes/encoding; the teaching caller owns lesson content. Return ordinary audio and measured duration; do not import or modify sibling packages. Creation grants no publication.

Run scripts/list_options.py for supported local routes without importing engines. Compare the actual device/dependencies/cache before proposing options: Qwen3 0.6B CustomVoice MLX 5bit is the Apple Silicon recommendation, ppaso ONNX CPU the lightweight Korean option; retain explicit Qwen MLX 8bit and official PyTorch. Discovery is not runtime/model readiness or a quality ranking. Supertonic 3 ONNX CPU/F1 is an explicit alternative, not a new default. Its upstream is archived. When selected, tell the user that AI-synthesis disclosure is required and return the receipt's disclosure_required and disclosure_notice; do not claim the audio/video was automatically labeled. Present every list_options.py route with its device/platform, voices and dependency/cache setup status; past evaluations affect recommendations only, never which engines are shown. Reuse the ordinary-chat question format below and retain unsupported/uninstalled routes with their limits. Read installation and pins before verification, download or synthesis. Reuse verified setup and matching approval. Resolve material engine/voice choices before work; never silently switch engines after a failure or install into a global environment.