Lanson ReceptionLanson LiveLanson FlowLanson PodcastTechnologyAbout UsBlogExperience Lanson

    Apps

    Lanson LiveLanson Flow

    Preferences

    Language

    Cookbook

    Executable how-tos for building with the realtime API — real endpoints, runnable pipelines, and the traps we hit so you don't have to.

    Basicsbeginner

    How to choose between realtime and batch transcription

    Realtime WebSocket, Segment HTTP, or Batch jobs? The decision isn't 'do I need it live' — it's who does VAD and what happens to silence. A decision table and a minimal example for each plane.

    7 minHow-to
    Basicsintermediate

    How to stream microphone audio over WebSocket

    Your browser gives you float32 at 48kHz stereo; the realtime API wants PCM16LE at 16kHz mono in 100ms frames. The full capture → convert → frame → send pipeline, plus backpressure and reconnect.

    9 minHow-to
    Basicsbeginner

    How to build realtime captions that don't jitter

    Live captions that flicker and rewrite themselves destroy trust. Here's the StableStream model: the API only emits stable text, so your client is append-only — no partial→final replacement, no rollback, no debounce.

    8 minHow-to

    Voice Context Layer

    Turning live speech into stable context, interaction, and action.

    Products

    • Lanson Reception
    • Lanson Live
    • Lanson Flow
    • Lanson Podcast

    Solutions

    • Voice Agents
    • Live Transcription
    • Voice Input
    • Events & Conferences

    Technology

    • Voice Context Layer
    • Trinity Engine
    • StableStream

    Developers

    • Developer Platform
    • Documentation
    • Service Status

    Resources

    • Blog
    • Updates
    • Help Center

    Company

    • About Us
    • Our Philosophy
    • Contact

    © 2026 LansonAI Inc.

    Privacy PolicyTermsCookie Policy

    Cookies & analytics

    We use essential cookies to run this site. If you allow, we also load Vercel Analytics to measure visits. Read the Cookie Policy