[{"data":1,"prerenderedAt":4},["ShallowReactive",2],{"article-doc:docs\u002Fconcepts\u002F7.trinity-engine":3},"---\ntitle: Trinity Engine\ndescription: The shared processing foundation behind LansonAI's real-time voice capabilities.\n---\nTrinity Engine is the shared processing foundation behind LansonAI's real-time voice capabilities.\n\nIt sits below product experiences and developer-facing APIs.\n\nConceptually:\n\n```text\nLanson Live\nLanson Reception\nDeveloper APIs\n        ↓\n   Trinity Engine\n        ↓\nSpeech and context infrastructure\n```\n\n## What Trinity Engine does\n\nTrinity Engine coordinates the processing required to turn incoming speech into application-ready context.\n\nThis includes multiple stages that may operate at different timescales, such as:\n\n- speech processing\n- segmentation\n- contextual interpretation\n- correction\n- stabilization\n- multilingual processing\n\nThe exact internal implementation may evolve independently of the developer-facing API.\n\n## Why the separation matters\n\nApplications should not need to understand the internal processing architecture in order to use LansonAI.\n\nThe developer contract exists at the API layer.\n\nTrinity Engine exists below that contract.\n\nThis separation allows LansonAI to improve its internal speech and context processing while keeping application integrations stable.\n\n## Relationship to StableStream\n\nTrinity Engine and StableStream describe different layers.\n\n**Trinity Engine**\nThe processing foundation.\n\n**StableStream**\nThe behavior and continuity of evolving context exposed to live applications.\n\nThis distinction is important because the developer experience should be defined by observable behavior rather than internal implementation details.\n",1790059118949]