Model statecharts just by describing them.
Now your AI Agents can finally talk back! Professional TTS voice for Claude Code, Claude Desktop (via MCP), and Clawdbot with multi-provider support.
Voice-cloning + LLM-narration client for Builderforce.ai Studio. One resolveNarrationEngine() seam routes text→speech through an on-device SSM clone engine (WebGPU, $0) or the metered gateway synthesize endpoint, with an honest named-voice fallback. Consu
glissade narration + captions: TTS at prepare time (gs narrate), deterministic caching, narration-anchored timeline beats, and captions as plain tracks. Render stays offline.
glissade sound effects: a clean-room procedural (sfxr-style) synth, license-checked sample packs, and deterministic index-seeded variation — committed WAVs feed the same offline FFmpeg mix as narration and music.
Teach an AI agent how to use any website. Once. Records a real browser session + narration; generates a deterministic MCP tool plus a DOM-replay playbook fallback.