GPT-5.6 Sol API and credit pricing cut by over 20%Claude Security now scans GitHub repos with Mythos 5 Zero Data Retention continues with Private Safety Processing preview for stronger safety Claude can now send Gmail emails and manage Google Drive files Strengthen monitoring for high-risk training and pause RL runs Approved defenders can advance advanced vulnerability research with GPT-5.6-Cyber Cyclone forecasts now provide over a day of extra lead time Talk while reasoning or using tools without conversation breaks AI delivers new results on 10 long-standing math problems with proofs released GPT-5.6 Luna and Terra prices drop 80% and 20%, with faster Sol option added Opus 5 now available on all paid plans and API Securely link health records to understand symptom changes and test results in context Run code inside notes for deeper analysis GPT-Red boosts prompt injection resistance significantly Cut lesson prep time with AI You can move from conversation to documents faster Run AI inference in the browser and cut wait time Review how you use Claude and cut waste Long tasks can move from draft to presentation more easily Track the latest safety rules for bigger models GPT-5.6 Sol API and credit pricing cut by over 20%Claude Security now scans GitHub repos with Mythos 5 Zero Data Retention continues with Private Safety Processing preview for stronger safety Claude can now send Gmail emails and manage Google Drive files Strengthen monitoring for high-risk training and pause RL runs Approved defenders can advance advanced vulnerability research with GPT-5.6-Cyber Cyclone forecasts now provide over a day of extra lead time Talk while reasoning or using tools without conversation breaks AI delivers new results on 10 long-standing math problems with proofs released GPT-5.6 Luna and Terra prices drop 80% and 20%, with faster Sol option added Opus 5 now available on all paid plans and API Securely link health records to understand symptom changes and test results in context Run code inside notes for deeper analysis GPT-Red boosts prompt injection resistance significantly Cut lesson prep time with AI You can move from conversation to documents faster Run AI inference in the browser and cut wait time Review how you use Claude and cut waste Long tasks can move from draft to presentation more easily Track the latest safety rules for bigger models

Official sources only. Rumors, leaks, and get-rich schemes are excluded.

← Back to top

AI BriefingOpenAIGuides & Tips16:35

AI summarized from verified sources

Perplexity Scales Voice Search to Millions with Realtime API

Build stable voice agents in noisy environments for better UX.

SOURCE CHECK

2 sources

VERIFIED

Sources

Primary / x.com

Official Blog

Supporting / developers.openai.com

Official Blog

Key Points

1Incremental 2k token chunks for context.
2Rust SDK standardizes 48kHz Opus audio.
3Voice lock prevents interruptions.
4Narrow tools ensure stable JSON outputs.

Perplexity used OpenAI's Realtime API for voice search in Comet and Computer, handling millions of sessions monthly. Optimized context in 2k token chunks and audio pipelines with Rust SDK. Developers can now replicate production-grade low-latency voice agents easily.

What changed

Perplexity used OpenAI's Realtime API for voice search in Comet and Computer, handling millions of sessions monthly. Optimized context in 2k token chunks and audio pipelines with Rust SDK. Developers can now replicate production-grade low-latency voice agents easily.

Why it matters

Build stable voice agents in noisy environments for better UX.

What to watch

Build stable voice agents in noisy environments for better UX. Key checks: Incremental 2k token chunks for context. / Rust SDK standardizes 48kHz Opus audio. / Voice lock prevents interruptions..