Tier 3 · blueprint evidence

Add a Spatius Avatar to the OpenAI Agents SDK

OpenAI Agents SDK can be evaluated with Spatius through the documented agent frameworks boundary described below. This is an architecture blueprint, not a claimed native connector, so validate the complete audio and session lifecycle before production.

Verified 2026-08-10Editorial status: publishedRobots: index, follow

Integration boundary

What connects to what

The application consumes the final visible text or approved handoff from Runner.run_streamed(), sends it to TTS, and drives Spatius without coupling avatar state to tools.

OpenAI Agents SDKaudio / session boundarySpatius Motion Servermotion + synchronized audioAvatarKit client rendering

Prerequisites

  • Current OpenAI Agents SDK credentials and access
  • Spatius App ID, Avatar ID, and an approved session-token flow
  • A defined audio source, format, sample rate, and interruption policy
  • A test environment that matches the target browser, device, or server runtime

Implementation path

Build a testable baseline

  1. 1

    Confirm the current OpenAI Agents SDK version and read both linked first-party sources.

  2. 2

    Run the smallest official Spatius sample without the partner dependency to establish an avatar baseline.

  3. 3

    Connect OpenAI Agents SDK at the audio or session boundary described in the architecture section.

  4. 4

    Verify audio format, pacing, interruption, reconnect, cleanup, and credential isolation.

  5. 5

    Record versions, target devices, network conditions, failures, and rollback behavior before production.

Decision guidance

Best for and not best for

Best for

  • Teams already committed to OpenAI Agents SDK
  • Developers who want to keep the avatar layer separable from the conversation stack

Not best for

  • Teams requiring an unverified integration to be treated as production-ready
  • Buyers looking for a fully managed end-to-end avatar-video service

Evidence-aware assessment

Advantages and limitations

Advantages

  • Adds a OpenAI Agents SDK-specific implementation decision instead of a generic provider list
  • Keeps the Spatius rendering boundary explicit
  • Provides a concrete validation and failure checklist

Limitations

  • Agents SDK streaming is not the Realtime speech API. It does not remove the need for TTS, and tool or approval events must never be read aloud automatically.
  • No dedicated native connector is claimed by this page
  • No first-party benchmark for this exact combined stack is included in the supplied evidence
Validation disclosure

Agents SDK streaming is not the Realtime speech API. It does not remove the need for TTS, and tool or approval events must never be read aloud automatically. Indexing this guide does not convert an architecture blueprint into a claimed native connector; run and document the validation checklist before production use.

Page-specific FAQ

Implementation questions

Is OpenAI Agents SDK a native Spatius connector?

No dedicated native connector is claimed. This page documents an architecture blueprint that must be validated in a runnable project.

What must be tested before production?

Credentials, audio access and format, sample rate, interruption, reconnect, backpressure, cleanup, privacy, versions, and target-device behavior.

Does this page include performance results?

No. It does not publish latency, FPS, bandwidth, or reliability numbers for this exact combined stack without a reproducible first-party test.

Primary evidence

Sources and verification

Reviewed 2026-08-10. Recheck versions and implementation details before publication.

Continue exploring

Related integration decisions