Minh/s2s context summary

[minh-hoque]

Summary

This PR introduces a fully-worked Jupyter notebook, examples/Context_summarization_with_realtime_api.ipynb, that demonstrates how to:

1. Stream live microphone audio into the OpenAI Realtime (voice-to-voice) API via WebSockets.
2. Play assistant speech back in near-real-time.
3. Track running token usage for both text and audio tokens.
4. Auto-summarize and prune older turns once the context window nears a configurable threshold (demo ≈ 2 k)

Motivation

Long-running voice sessions quickly accumulate LARGE amounts of audio tokens, causing latency and quality drift. This demo provides a reference implementation of rolling summarization that compresses earlier dialogue into a single assistant message (in French for the demo), deletes superseded items server-side, and keeps only the last N turns verbatim—saving cost and preserving quality.

---

For new content

When contributing new content, read through our contribution guidelines, and mark the following action items as completed:

• I have added a new entry in registry.yaml (and, optionally, in authors.yaml) so that my content renders on the cookbook website.
• I have conducted a self-review of my content based on the contribution guidelines:
  • Relevance: This content is related to building with OpenAI technologies and is useful to others.
  • Uniqueness: I have searched for related examples in the OpenAI Cookbook, and verified that my content offers new insights or unique information compared to existing documentation.
  • Spelling and Grammar: I have checked for spelling or grammatical mistakes.
  • Clarity: I have done a final read-through and verified that my submission is well-organized and easy to understand.
  • Correctness: The information I include is correct and all of my code executes successfully.
  • Completeness: I have explained everything fully, including all necessary references and citations.

We will rate each of these areas on a scale from 1 to 4, and will only accept contributions that score 3 or higher on all areas. Refer to our contribution guidelines for more details.