Video sessions

Video sessions take the same agent and put a face on it. Saaya runs WebRTC over our real-time media pipeline, drives a photorealistic avatar through our avatar layer, and streams the model output through it in real time.

Starting a video session

video.ts
const session = await saaya.sessions.create({
  agentId: "agt_2N3rH...",
  channel: "video",
  avatar:  { provider: "saaya", replicaId: "rep_abc" },
});

// Hand the session token to the browser to join the room.
console.log(session.roomUrl, session.roomToken);

Avatar overlay

Avatars run as a video track in the media room. You can render them full-screen, in a picture-in-picture, or with a custom overlay (logo, captions, presenter title). Captions are served as a separate text track so screen readers and search index them.

Accessibility

  • Live captions on by default, with a toggle for the user.
  • Keyboard-only join + mute + leave, no mouse required.
  • Avatar carries a visible label ("This is an AI agent").
  • Audio-only fallback when bandwidth drops below 250kbps.

Recording

Video recording is opt-in. Saaya stores an MP4 with mixed audio plus the per-track transcript. Recordings live in your residency region and can be exported to object storage or fetched via `sessions.exports`.

Tuning the avatar

Different avatar providers have different latency / fidelity trade-offs, some ship the lowest first-frame time, others tend to feel more lifelike on long sessions. Try two and switch in the dashboard.
PreviousVoice (SIP, PSTN)NextBusiness messaging
Was this page helpful?