One prompt can now drive more of your work More support for defending infrastructure and open source See Claude’s rules updated for newer risks GPT-6 Intelligent UI makes conversations visual and interactive Claude Haiku 5.5 delivers low-cost, high-performance AI Create visual, interactive answers from a simple chat Run high-volume tasks with a cheaper fast model Share new mathematical results on GitHub to accelerate research Easier access to advanced Claude models for security work Run image, audio, and video search on-device with one model Atlassian integration makes company knowledge easier to use Decisions beta speeds up typed answers from text and images Anthropic expands safer access to advanced cyber features Enable text watermarking via API for EU compliance Claude training becomes easier for enterprise teams Anthropic invests in workforce training for enterprise adoption Enterprise adoption and training get easier Google's Gemini 4 Argon makes heavy tasks easier to offload Gemini 4 Argon is built for long professional tasks Use Astra-level performance affordably in daily work One prompt can now drive more of your work More support for defending infrastructure and open source See Claude’s rules updated for newer risks GPT-6 Intelligent UI makes conversations visual and interactive Claude Haiku 5.5 delivers low-cost, high-performance AI Create visual, interactive answers from a simple chat Run high-volume tasks with a cheaper fast model Share new mathematical results on GitHub to accelerate research Easier access to advanced Claude models for security work Run image, audio, and video search on-device with one model Atlassian integration makes company knowledge easier to use Decisions beta speeds up typed answers from text and images Anthropic expands safer access to advanced cyber features Enable text watermarking via API for EU compliance Claude training becomes easier for enterprise teams Anthropic invests in workforce training for enterprise adoption Enterprise adoption and training get easier Google's Gemini 4 Argon makes heavy tasks easier to offload Gemini 4 Argon is built for long professional tasks Use Astra-level performance affordably in daily work

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..