# Low Latency Low latency is the ability of a computing system or network to provide responses with minimal delay. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Accelerating Operational Efficiency in Modern Transportation DevFeed: [Accelerating Operational Efficiency in Modern Transportation]() Original publisher: [Read original article]() Author: Emily Kasman Published: 2026-09-17T13:30:51Z Content type: article Language: en Sources: [Cisco Blogs]() Topics: [Cisco](), [Network](), [Critical Infrastructure](), [legacy](), [Low Latency](), [Security](), [observability](), [Resilience]() Tags: [cisco](), [cisco-connected-rail](), [cisco-industrial-ethernet-switches](), [cisco-industrial-routers](), [cisco-industrial-security](), [connected-roadways](), [critical-infrastructure](), [industrial-ai](), [industrial-iot](), [legacy](), [low-latency](), [modernization](), [network](), [observability](), [resilience](), [security](), [transportation]() ### AI overview This Cisco article discusses how transit and roadway agencies can modernize legacy network infrastructure. It presents secure, low-latency connectivity, end-to-end operational visibility, and security-focused architecture as ways to support real-time processing, connected systems, and more resilient transportation operations. ### Source excerpt Learn how Cisco helps transit agencies overcome legacy network bottlenecks with secure, AI-ready connectivity, full visibility, and robust cyber resilience. ## How NVIDIA Groq 3 LPX Deterministic Execution Drives Power-Efficient High-Interactivity Inference on NVIDIA Vera Rubin DevFeed: [How NVIDIA Groq 3 LPX Deterministic Execution Drives Power-Efficient High-Interactivity Inference on NVIDIA Vera Rubin]() Original publisher: [Read original article]() Author: Tanya Lenz Published: 2026-09-15T16:55:00Z Content type: article Language: en Sources: [NVIDIA Developer](), [NVIDIA Technical Blog]() Topics: [Groq 3 LPX](), [LPX](), [NVIDIA Vera Rubin](), [Vera Rubin NVL72](), [groq](), [Inference](), [Low Latency](), [long-context]() Tags: [agentic-ai-generative-ai](), [ai-factory](), [ai-inference](), [ai-platform](), [drive](), [dsx](), [groq](), [groq-3-lpx](), [inference](), [inference-performance](), [latency](), [low-latency](), [lpx](), [nvidia-vera-rubin](), [nvl72](), [performance](), [power-management](), [vera-rubin](), [vera-rubin-nvl72]() ### AI overview This NVIDIA developer article explains how Groq 3 LPX uses deterministic execution across 256 LPU chips to support low-latency inference on NVIDIA Vera Rubin. It describes compiler-scheduled execution and power-management techniques including Preemptive Power and Clock Period Synthesis. ### Source excerpt Power is a defining constraint for AI factories. As AI workloads demand a full compute platform to serve them, each component of that platform must maximize... ## How to operate shared platforms safely at agent scale DevFeed: [How to operate shared platforms safely at agent scale]() Original publisher: [Read original article]() Author: Candace Shamieh; T Zhang; Gabriele Baldoni Published: 2026-09-15T00:00:00Z Content type: article Language: en Sources: [Datadog | The Monitor blog]() Topics: [Platform Engineering](), [Loop Engineering](), [AI Agent](), [sdlc](), [Latency](), [Low Latency](), [Concurrency](), [Software]() Tags: [agent](), [agent-observability](), [agentic-workflows](), [agents](), [ai](), [ai-agent](), [ci](), [concurrency](), [latency](), [low-latency](), [operational](), [performance](), [platform-engineering](), [platforms](), [queue](), [recovery](), [timeout]() ### AI overview This Datadog article explains how platform teams can operate shared platforms safely as AI agent workloads scale across teams. It discusses modeling demand across agent trajectories, planning capacity across dependencies such as CI queues and sandbox pools, handling contention and recovery behavior, and preserving control across system boundaries. ### Source excerpt Learn how Datadog models agent demand, allocates capacity under contention, and preserves control as AI agent workloads scale across shared platforms. ## 🍔🧠 Pinterest's Fix for the Hardest Problem in ML Infra DevFeed: [🍔🧠 Pinterest's Fix for the Hardest Problem in ML Infra]() Original publisher: [Read original article]() Author: Alexandre Zajac Published: 2026-09-14T15:31:30Z Content type: article Language: en Sources: [Hungry Minds]() Topics: [recommendation systems](), [Feature Engineering](), [Inference](), [Streaming](), [configuration](), [Framework](), [data](), [Low Latency]() Tags: [batch](), [configuration](), [data](), [feature-engineering](), [low-latency](), [ml](), [pinterest](), [ranking](), [recommendation-systems](), [streaming]() ### AI overview Pinterest redesigned its user-sequence platform for ranking, retrieval, and recommendation systems by defining signals once and instantiating them consistently across streaming, batch, and serving workloads. The approach uses Python configuration with validated schemas, a shared execution engine, cooperating streaming and batch paths, and columnar time-partitioned storage to improve freshness, completeness, consistency, and operational efficiency. ### Source excerpt PLUS: OpenAI agents beat math 🧮, Test techniques for agents ⚡, Postgres survival guide 📖 ## Infineon RISC-V for Automotive at Hot Chips 2026 DevFeed: [Infineon RISC-V for Automotive at Hot Chips 2026]() Original publisher: [Read original article]() Author: Vic A Published: 2026-09-13T21:58:44Z Content type: article Language: en Sources: [ServeTheHome]() Topics: [RISC-V](), [Microcontroller](), [real-time](), [Low Latency](), [Architecture & Design](), [Security](), [IO](), [Inference Performance]() Tags: [2026](), [architecture](), [automotive](), [compute](), [cost](), [efficiency](), [infineon](), [latency](), [low-latency](), [microcontrollers](), [mobile](), [performance](), [posix](), [processors](), [real-time](), [risc-v](), [security]() ### AI overview Infineon presents RISC-V automotive processors for next-generation vehicle architectures. The article covers real-time control, low latency, power efficiency, security, zone controllers, central car computers, and heterogeneous workloads including DSP, AI inference, audio, and POSIX-based services. ### Source excerpt At Hot Chips 2026, Infineon presented a case for using RISC-V in various automotive processors in next-generation cars The post Infineon RISC-V for Automotive at Hot Chips 2026 appeared first on ServeTheHome. ## Patches Ready For AMDGPU HDMI 2.1 Enabled By Default With Linux 7.4 With FreeSync, VRR & ALLM DevFeed: [Patches Ready For AMDGPU HDMI 2.1 Enabled By Default With Linux 7.4 With FreeSync, VRR & ALLM]() Original publisher: [Read original article]() Author: Michael Larabel Published: 2026-09-11T10:39:00Z Content type: news Language: en Sources: [Phoronix]() Topics: [hdmi](), [Linux](), [Low Latency](), [Code]() Tags: [code](), [desktop-linux](), [driver](), [gaming](), [graphics](), [hdmi](), [kernel](), [latency](), [linux](), [linux-benchmarking](), [linux-hardware-benchmarks](), [linux-hardware-reviews](), [linux-how-to](), [linux-performance](), [linux-server-benchmarks](), [low-latency](), [open](), [open-source-graphics](), [phoronix](), [phoronix-test-suite](), [release](), [ubuntu-benchmarks](), [ubuntu-hardware](), [updates]() ### AI overview The article reports that most AMDGPU HDMI 2.1 support is expected to merge for Linux 7.4 and be enabled by default. The work includes FreeSync, VRR, ALLM, and HDMI FRL support, along with updates to AMD graphics and display engines. ### Source excerpt Linux 7.4 is now set to reach the elusive milestone of HDMI 2.1 support for the AMDGPU kernel graphics driver. After the HDMI Forum previously rejected HDMI 2.1 for the AMDGPU open-source driver implementation going back years, earlier this year something changed -- widely speculated to be with Valve's involvement -- that HDMI 2.1 patches began appearing for the AMDGPU driver. With the upcoming Linux 7.4 cycle, the bulk of that work will now be in place and enabled by default... ## Adaptive Instructed-Retriever: Frontier-Quality Search at 2x Lower Latency DevFeed: [Adaptive Instructed-Retriever: Frontier-Quality Search at 2x Lower Latency]() Original publisher: [Read original article]() Author: Cindy Wang; Cheng Li; Jialu Liu; Sean Kulinski; Arnav Singhvi; Wen Sun; Michael Bendersky Published: 2026-09-09T13:30:00Z Content type: article Language: en Sources: [Databricks]() Topics: [databricks](), [Latency](), [Low Latency](), [data]() Tags: [agents](), [announcements](), [benchmarks](), [cost](), [data](), [databricks](), [enterprise](), [latency](), [low-latency](), [performance](), [platform](), [retrieval](), [search](), [speed](), [third-party]() ### AI overview Databricks introduces Adaptive Instructed-Retriever, a retrieval model that combines fast parallel search with sequential multi-step search for harder enterprise queries. It adaptively spends extra computation only when useful, achieving comparable quality to leading third-party models at twice lower latency while improving over single-step retrieval on reported benchmarks. ### Source excerpt Effective enterprise data agents require search that is both accurate and fast. Earlier... ## Video Streaming Technology: Protocols, Codecs, CDNs, and 2026 Trends DevFeed: [Video Streaming Technology: Protocols, Codecs, CDNs, and 2026 Trends]() Original publisher: [Read original article]() Author: Jon Whitehead Published: 2026-09-08T01:00:42Z Content type: tutorial Language: en Sources: [DaCast]() Topics: [Streaming](), [5G](), [Artificial Intelligence](), [Low Latency](), [real-time](), [WebRTC](), [Virtual reality]() Tags: [access-control](), [ai](), [cdn](), [encryption](), [guide](), [latency](), [low-latency](), [streaming](), [technology](), [the-video-experts-blog](), [video](), [video-streaming]() ### AI overview This guide explains how video streaming works, covering data encoding, delivery through content delivery networks, decoding by video players, streaming protocols, codecs, and security. It also discusses AI-driven tools, low-latency streaming, 5G, edge computing, virtual reality, and business applications in 2026. ### Source excerpt By Dacast Editorial Team | Reviewed by Jon Whitehead, COO at Dacast | Updated September 2026 Video streaming technology has revolutionized the way businesses and individuals share and consume content. Whether it's live streaming a product launch, hosting virtual events, delivering training sessions, or providing entertainment through on-demand video services, streaming technology is now an [...] The post The Definitive Guide to Video Streaming Technology in 2026 appeared first on Dacast. ## Choosing a low-latency infrastructure layer for conversational AI DevFeed: [Choosing a low-latency infrastructure layer for conversational AI]() Original publisher: [Read original article]() Author: Luke Morgan Published: 2026-09-08T00:00:00Z Content type: article Language: en Sources: [Twilio Blog]() Topics: [Low Latency](), [Conversational AI](), [Artificial Intelligence](), [systems]() Tags: [conversational-ai](), [industry-insights](), [inference](), [infrastructure](), [low-latency](), [real-time](), [voice-ai]() ### AI overview This article explains how infrastructure choices affect latency in conversational AI call-center systems. It describes a unified path for speech recognition, language-model processing, and speech synthesis, and presents Twilio's ConversationRelay as a low-latency voice pipeline with median latency under 0.5 seconds. ### Source excerpt ConversationRelay delivers real-time speech recognition for call centers, with under 0.5s median latency. See how Twilio powers low-latency conversational AI. ## 🍔🧠 How OpenAI Built GPT-Live for Low-Latency Voice AI DevFeed: [🍔🧠 How OpenAI Built GPT-Live for Low-Latency Voice AI]() Original publisher: [Read original article]() Author: Alexandre Zajac Published: 2026-09-07T15:31:33Z Content type: article Language: en Sources: [Hungry Minds]() Topics: [Conversational AI](), [Low Latency](), [voice ai](), [OpenAI](), [real-time](), [Streaming](), [Remote Procedure Call (RPC)](), [Go]() Tags: [go](), [low-latency](), [openai](), [real-time](), [rpc](), [software-engineering](), [streaming](), [voice-ai]() ### AI overview The article explains how OpenAI built GPT-Live as a low-latency, full-duplex voice system. It describes a fast audio path that listens and speaks simultaneously, asynchronous delegation of deeper reasoning and backend work, stateful handoffs, optimized protocol boundaries, and a Go-based media frontend. ### Source excerpt PLUS: Zero-knowledge proofs ⚡, Design.md agent automation 👨💻, System Design Docs 101 📚 ## VDURA Deploys High-Performance Storage Platform for AI and HPC at New Mexico State University DevFeed: [VDURA Deploys High-Performance Storage Platform for AI and HPC at New Mexico State University]() Original publisher: [Read original article]() Author: Harold Fritts Published: 2026-09-02T10:00:00Z Content type: news Language: en Sources: [StorageReview.com]() Topics: [Artificial Intelligence](), [High-Performance Computing](), [Data Infrastructure](), [InfiniBand](), [Post-quantum cryptography](), [Deployment](), [Training AI Models](), [Hardware](), [Low Latency](), [Quantum Computing]() Tags: [ai](), [data-infrastructure](), [deployment](), [enterprise](), [enterprise-storage](), [hardware](), [high-performance-computing](), [infiniband](), [low-latency](), [post-quantum-cryptography-pqc](), [quantum](), [storage]() ### AI overview VDURA has moved its storage platform at New Mexico State University into full production to support AI and high-performance computing research. The deployment combines NVMe flash and high-density HDD tiers through a global namespace over InfiniBand, allowing separate scaling of performance and capacity. It also supports NMSU's post-quantum cryptography research and large-scale data pipeline projects. ### Source excerpt VDURA has completed the deployment of its data platform at New Mexico State University (NMSU), moving the system into full production. The infrastructure is designed to serve the university's research community with a high-durability, high-throughput storage environment tailored specifically for artificial intelligence and high-performance computing (HPC) workloads. NMSU, which holds Carnegie R1 status and manages The post VDURA Deploys High-Performance Storage Platform for AI and HPC at New Mexico State University appeared first on StorageReview.com. ## Video Streaming Protocols: 6 Preferred Formats for Professional Broadcasting DevFeed: [Video Streaming Protocols: 6 Preferred Formats for Professional Broadcasting]() Original publisher: [Read original article]() Author: Jon Whitehead Published: 2026-09-02T09:35:50Z Content type: tutorial Language: en Sources: [DaCast]() Topics: [Streaming](), [Protocol (disambiguation)](), [Latency](), [Low Latency](), [WebRTC](), [Playback](), [format](), [data]() Tags: [data](), [format](), [latency](), [low-latency](), [playback](), [protocols](), [streaming](), [the-video-experts-blog](), [video](), [video-streaming](), [webrtc]() ### AI overview This guide explains six video streaming protocols used in professional broadcasting: HLS, RTMP, WebRTC, SRT, RTSP, and MPEG-DASH. It compares their purposes, strengths, limitations, latency, compatibility, and suitable use cases. It presents HLS as a broadly compatible delivery default, RTMP as an ingest standard, WebRTC for real-time two-way interaction, SRT for one-way broadcasting over unreliable networks, RTSP for surveillance and IoT, and MPEG-DASH as an open alternative with limited Apple support. ### Source excerpt By Dacast Editorial Team | Reviewed by Jon Whitehead, COO at Dacast | Updated September 2026 A video streaming protocol is the set of rules that governs how video data moves from your encoder to your streaming host to the video player your audience watches on. Common examples include RTMP, HLS, WebRTC, and SRT, each [...] The post Video Streaming Protocols: 6 Preferred Formats for Professional Broadcasting appeared first on Dacast. ## Postgres + ClickHouse Architectural Patterns DevFeed: [Postgres + ClickHouse Architectural Patterns]() Original publisher: [Read original article]() Author: Agus Syafaat Published: 2026-08-26T08:08:43Z Content type: article Language: en Sources: [SeveralNines]() Topics: [clickhouse](), [PostgreSQL](), [Databases](), [Architecture & Design](), [data-platforms](), [real-time](), [Transactions](), [Low Latency](), [dashboards]() Tags: [analytics](), [architecture](), [clickhouse](), [clustercontrol](), [database-general](), [hybrid-operations](), [latency](), [olap](), [postgres](), [postgresql](), [real-time](), [time](), [transactions]() ### AI overview This article explains architectural patterns that combine PostgreSQL and ClickHouse. PostgreSQL serves as the authoritative transactional system for OLTP workloads, while ClickHouse handles large-scale analytical queries and real-time analytics. Continuous Change Data Capture synchronization connects the systems and separates transactional and analytical workloads. ### Source excerpt The role of databases has shifted significantly as modern applications must deliver real-time analytics, dashboards, and machine learning alongside low-latency transaction processing. Handling these diverse demands with a single relational database has become unsustainable under growing data volumes. Consequently, organizations are adopting specialized database architectures where multiple engines work together based on their strengths, allowing [...] The post Postgres + ClickHouse Architectural Patterns appeared first on Severalnines. ## Golden Paths for AI agents: What changes when platform users aren't human? DevFeed: [Golden Paths for AI agents: What changes when platform users aren't human?]() Original publisher: [Read original article]() Author: Candace Shamieh; Shlomo Benyaminov; James Eastham Published: 2026-08-25T00:00:00Z Content type: article Language: en Sources: [Datadog | The Monitor blog]() Topics: [Artificial Intelligence](), [Software Engineering](), [API](), [Low Latency](), [Provisioning](), [real-time]() Tags: [agent-observability](), [agentic](), [agents](), [ai](), [ai-agents](), [ai-security](), [api](), [autonomous](), [developers](), [engineering](), [how-to](), [latency](), [low-latency](), [platform](), [platform-engineering](), [real-time](), [sandbox](), [software-engineering](), [workflow](), [workflows]() ### AI overview Golden Paths for AI agents must evolve beyond human-oriented development workflows. The article explains how platform teams can design agent-facing paths around workload requirements, machine-consumable and enforceable platform capabilities, execution patterns, and controlled workflow dispatch. ### Source excerpt Golden Paths for AI agents require intentional execution patterns, machine-consumable contracts, and dispatch controls. Here's how to build them. ## MetaRoCE: A New RDMA Transport Built for AI-Scale Ethernet DevFeed: [MetaRoCE: A New RDMA Transport Built for AI-Scale Ethernet]() Original publisher: [Read original article]() Author: Arvind Srinivasan; Neil Spring; Omar Baldonado; Rajiv Krishnamurthy Published: 2026-08-24T18:02:29Z Content type: article Language: en Sources: [Engineering at Meta]() Topics: [Ethernet](), [Networks](), [AI Infrastructure](), [GPU](), [data centers](), [Low Latency](), [telemetry](), [Inference]() Tags: [ai-infrastructure](), [data-center-engineering](), [data-centers](), [data-infrastructure](), [ethernet](), [gpu](), [low-latency](), [networking-traffic](), [open-source](), [performance](), [real-time](), [telemetry]() ### AI overview Meta introduces MetaRoCE, an RDMA transport protocol designed for AI workloads on commodity Ethernet at million-GPU scale. The article describes its release through the Open Compute Project and explains how endpoint intelligence, packet spraying, fine-grained logical paths, and real-time telemetry aim to provide high throughput, low tail latency, and operational simplicity for distributed training and inference. ### Source excerpt Training and serving frontier AI models depends on fast, reliable networks that move data between GPUs without wasting compute cycles. To meet this challenge at scale, Meta designed MetaRoCE - a clean-sheet RDMA transport protocol purpose-built for AI workloads on commodity Ethernet. We're releasing the MetaRoCE specification, a reference software implementation and a compliance test [...] Read More... The post MetaRoCE: A New RDMA Transport Built for AI-Scale Ethernet appeared first on Engineering at Meta. ## How XPUs Meet a World-Class AI Factory DevFeed: [How XPUs Meet a World-Class AI Factory]() Original publisher: [Read original article]() Author: Jesse Clayton Published: 2026-08-24T15:00:54Z Content type: article Language: en Sources: [NVIDIA Blog]() Topics: [AI Factory](), [NVLink](), [AI Infrastructure](), [Network](), [networking](), [Low Latency](), [moe](), [Artificial Intelligence](), [Nvidia](), [AI Platform](), [Latency]() Tags: [agentic-ai](), [ai-factory](), [ai-infrastructure](), [ecosystem](), [ethernet](), [gb300-nvl72](), [hardware](), [mixture-of-experts](), [networking](), [nvidia-dsx](), [nvl72](), [nvlink](), [software](), [time](), [xpu]() ### AI overview The article explains how NVLink Fusion combines custom XPUs with NVIDIA's established AI infrastructure to help build semi-custom AI factories. It focuses on scale-up networking, performance, resiliency, telemetry, platform maturity, and the economics of large-scale AI workloads. ### Source excerpt To generate intelligence at scale, AI factories run continuously, and their economics are defined by delivered output: tokens per second, tokens per watt, cost per token, utilization and uptime. That requires AI infrastructure designed and built as a full factory, not a collection of individual accelerators. Hyperscalers and AI-native companies building custom XPUs must consider [...] ## How Sprig Replaced Postgres, ClickHouse & Redis...with 4-8x Better Latency DevFeed: [How Sprig Replaced Postgres, ClickHouse & Redis...with 4-8x Better Latency]() Original publisher: [Read original article]() Author: Cynthia Dunlop Published: 2026-08-24T13:30:56Z Content type: article Language: en Sources: [ScyllaDB]() Topics: [Latency](), [Low Latency](), [Databases](), [PostgreSQL](), [clickhouse](), [Redis](), [real-time](), [Back end](), [recommendation systems](), [Artificial Intelligence]() Tags: [backend](), [clickhouse](), [data](), [databases](), [engineering](), [latency](), [low-latency](), [postgres](), [postgresql](), [real-time](), [recommendation-systems](), [redis](), [user-stories]() ### AI overview Sprig outgrew PostgreSQL as its AI-powered product research platform scaled to more than 1.3 trillion events, 75 billion attributes, and high-volume real-time processing. The article describes its database challenges and the path toward lower-latency data infrastructure involving PostgreSQL, ClickHouse, and Redis. ### Source excerpt With ScyllaDB, a small engineering team could focus on building their product instead of battling their databases. ## Do IXPs make the Internet faster? It's complicated DevFeed: [Do IXPs make the Internet faster? It's complicated]() Original publisher: [Read original article]() Author: Dan Fidler Published: 2026-08-23T23:05:33Z Content type: article Language: en Sources: [APNIC Blog]() Topics: [Internet](), [networking](), [Latency](), [Network](), [Low Latency](), [Streaming](), [Caching](), [Cloud](), [Resilience](), [Routing (disambiguation)](), [datasets]() Tags: [australia](), [cloud](), [content](), [cost](), [events](), [global](), [infrastructure](), [internet](), [ixps](), [latency](), [local](), [low-latency](), [netflix](), [network](), [networks](), [performance](), [resilience](), [routing](), [streaming](), [tech-matters](), [technology](), [thailand](), [thainog]() ### AI overview IXPs do not make the Internet uniformly faster. Their impact depends on how performance is defined, where content is hosted or cached, the type of exchange, and the surrounding network conditions. The article examines latency, throughput, streaming quality, reliability, routing, and the changing meaning of keeping traffic local. ### Source excerpt IXPs shape latency, cost, resilience, and the spread of new technologies, not just Internet speed. As the Internet evolves, the role of IXPs continues to expand, as highlighted in this BPF 2026 panel discussion. ## Fish Audio models now available on Vercel AI Gateway for free DevFeed: [Fish Audio models now available on Vercel AI Gateway for free]() Original publisher: [Read original article]() Author: Jerilyn Zheng Published: 2026-08-19T00:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [voice ai](), [Vercel](), [asr](), [Streaming](), [Low Latency](), [SDKs]() Tags: [ai-gateway](), [audio](), [browser](), [free](), [launch](), [models](), [sdk](), [speech](), [streaming](), [text-to-speech](), [transcription](), [voice]() ### AI overview Fish Audio's text-to-speech and transcription models are available on Vercel AI Gateway. The models are free for 30 days, with AI SDK 7 support for speech generation and transcription, including timestamped segments and word-level timing. ### Source excerpt Fish Audio's audio models are now available on AI Gateway. To celebrate the launch, every Fish Audio model is free on AI Gateway for the next 30 days, through September 18. Capability Regular Through September 18 Text-to-speech $15.00 per million characters Free Speech-to-text $0.36 per hour of audio Free Four models from Fish Audio are available, including their latest text-to-speech model: fish-audio/s2.1-pro (text-to-speech): Built for low-latency streaming; clones a voice from a reference recording. fish-audio/transcribe-1 (transcription): Returns the text along with the duration of the audio and timestamped segments, down to individual words. fish-audio/s2-pro (text-to-speech): Covers around eighty languages and takes inline tags, plain-language directions written into the text itself, so you can change how a single word or phrase is delivered instead of setting one style for the whole request. fish-audio/s1 (text-to-speech): Reads text that can carry markers for emotion, tone, and sound effects. How to use models during the offer period Using the standard model name (i.e., fish-audio/s2.1-pro) is free, but will automatically begin billing when the offer period ends. To ensure you aren't billed after the free period, add the -free suffix to the standard name, and the model will stop serving when the offer ends (i.e., fish-audio/s2.1-pro-free). Speech and transcription ship in the current AI SDK 7 release. Text-to-speech Generate spoken audio from text with generateSpeech and write the result: Speech-to-text Transcribe recordings into text with transcribe. The audio can be a buffer, a base64 string, or a URL: Each segment carries the text and its start and end time in seconds, down to individual words. Playground You can also try the Fish Audio models without writing any code. Open the models list, click into a model, and send text or audio to hear or read the result in your browser. For a full overview of how to utilize audio models, refer to the speech quickst ## NVIDIA JetPack 7.2.1 Adds Agentic Video Skills and T3000 Emulation DevFeed: [NVIDIA JetPack 7.2.1 Adds Agentic Video Skills and T3000 Emulation]() Original publisher: [Read original article]() Author: Elizabeth Goodman Published: 2026-08-11T19:00:00Z Content type: article Language: en Sources: [NVIDIA Developer](), [NVIDIA Technical Blog]() Topics: [Jetson](), [SDKs](), [CUDA](), [GPU](), [AI Inference](), [Inference Performance](), [Latency](), [Low Latency](), [C++](), [Python](), [Artificial Intelligence](), [Automation]() Tags: [agentic-ai-generative-ai](), [ai-inference](), [automation](), [c-plus-plus](), [cuda](), [edge-computing](), [featured](), [gpu](), [inference](), [jetpack](), [jetson](), [latency](), [low-latency](), [nvidia](), [python](), [robotics](), [robotics-compute](), [sdks](), [video-analytics](), [video-codec-sdk]() ### AI overview NVIDIA JetPack 7.2.1 adds PyNvVideoCodec 2.2 support on Jetson Thor, enabling Python-based hardware video encoding and decoding with GPU-resident frames. It also introduces agentic video skills that turn developer goals into device inspection, configuration, execution, measurement, and evidence-driven codec workflows. ### Source excerpt Video is a core data path across NVIDIA Jetson applications, from robotics and intelligent video analytics to industrial automation, healthcare, media... ## Build Low-Latency Multilingual Voice Agents: Open Weights & Full Deployment Control with NVIDIA Magpie TTS DevFeed: [Build Low-Latency Multilingual Voice Agents: Open Weights & Full Deployment Control with NVIDIA Magpie TTS]() Original publisher: [Read original article]() Author: Maryam Motamedi; Mikyas Desta; Jason Li; Jason Roche Published: 2026-08-10T16:25:36Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [Low Latency](), [Latency](), [voice ai](), [NVIDIA NIM](), [Open Source Models & Datasets](), [asr](), [Conversational AI](), [Large Language Model](), [Automation]() Tags: [agents](), [ai](), [api](), [audio](), [automation](), [conversational-ai](), [data](), [developers](), [infrastructure](), [latency](), [llm](), [low-latency](), [model](), [models](), [nvidia](), [nvidia-nim](), [open](), [speech](), [text-to-speech](), [voice]() ### AI overview This developer article presents NVIDIA Magpie Multilingual TTS as an open-weights, 364M-parameter text-to-speech model for building low-latency multilingual voice applications. It explains how a self-managed cascaded ASR, TTS, and LLM architecture can provide deployment control, tuning, privacy, and predictable performance across 12 languages. ### Source excerpt Build Low-Latency Multilingual Voice Agents: Open Weights & Full Deployment Control with NVIDIA Magpie TTS Every voice interaction has a latency budget. By the time a user hears your application respond, you've already spent precious milliseconds capturing audio, transcribing speech, running an LLM, retrieving context, and generating a response. Text-to-speech (TTS) is the final step -- and the one users notice most. If speech generation is slow, the whole experience feels slow. ## Low-latency, high-throughput SQS event processing with AWS Lambda provisioned mode DevFeed: [Low-latency, high-throughput SQS event processing with AWS Lambda provisioned mode]() Original publisher: [Read original article]() Author: Ben Freiberg Published: 2026-08-10T13:42:03Z Content type: article Language: en Sources: [AWS Compute Blog]() Topics: [Amazon Simple Queue Service (SQS)](), [AWS Lambda](), [Latency](), [Low Latency](), [Amazon Web Services](), [Concurrency](), [Kafka](), [Internet of things](), [telemetry]() Tags: [amazon-simple-queue-service-sqs](), [amazon-sqs](), [apache-kafka](), [aws](), [aws-lambda](), [concurrency](), [event-driven](), [flash](), [fraud](), [kafka](), [latency](), [low-latency](), [payment-processing](), [real-time](), [telemetry]() ### AI overview AWS explains how provisioned mode for Amazon SQS event source mappings with AWS Lambda provides explicit control over event pollers to support low-latency, high-throughput event processing. The article describes default and provisioned scaling, concurrency limits, throughput, and use cases including real-time payments, fraud detection, IoT telemetry, and flash-sale order fulfillment. ### Source excerpt Customers building event-driven applications on AWS rely on Amazon Simple Queue Service (Amazon SQS) and AWS Lambda event source mappings (ESMs) to process millions of events every day. The fully managed polling infrastructure of ESMs eliminates the need to write and maintain custom code. You can focus on business logic while Lambda handles scaling, batching, [...] ## How we built a realtime system for responsive voice AI in six months DevFeed: [How we built a realtime system for responsive voice AI in six months]() Original publisher: [Read original article]() Published: 2026-08-03T07:00:00Z Content type: article Language: en Sources: [OpenAI News]() Topics: [voice ai](), [Low Latency](), [Inference](), [model-deployment](), [systems](), [Artificial Intelligence]() Tags: [agents](), [ai](), [architecture](), [audio](), [chatgpt](), [engineering](), [gpt](), [inference](), [latency](), [llm](), [llms](), [low-latency](), [model](), [speech](), [systems](), [text-to-speech](), [voice](), [voice-ai]() ### AI overview OpenAI describes GPT-Live, a full-duplex voice system designed for continuous, natural conversation. Its low-latency architecture streams audio in both directions, separates asynchronous delegation from the core voice path, and coordinates stateful inference, dynamic context management, and protocol-level optimization. ### Source excerpt GPT-Live enables continuous voice interaction with AI, using a turnless speech model and low-latency architecture for faster, more natural conversations. ## NVIDIA NVLink: The Scale-Up Network for AI Factories DevFeed: [NVIDIA NVLink: The Scale-Up Network for AI Factories]() Original publisher: [Read original article]() Author: Elizabeth Goodman Published: 2026-07-20T15:46:28Z Content type: article Language: en Sources: [NVIDIA Developer](), [NVIDIA Technical Blog]() Topics: [NVLink](), [AI Factory](), [AI Infrastructure](), [GPU](), [networking](), [Artificial Intelligence](), [Nvidia](), [datacenter](), [Latency](), [Mixture of Experts (MoE)](), [Inference Performance](), [Low Latency]() Tags: [agentic-ai-generative-ai](), [ai](), [ai-factory](), [ai-inference](), [ai-infrastructure](), [collective](), [communication](), [compute](), [data-center](), [featured](), [gpu](), [inference](), [infiniband](), [latency](), [low-latency](), [mixture-of-experts-moe](), [networking](), [nvidia](), [nvlink](), [production](), [scale](), [spectrum-ethernet](), [spectrum-x](), [speed](), [systems](), [vera-rubin]() ### AI overview NVIDIA NVLink is presented as a scale-up networking fabric for AI factories. It provides high-bandwidth, low-latency GPU-to-GPU communication for large AI inference, training, and parallel-computing workloads, with collective-operation acceleration and rack-level resiliency. ### Source excerpt The demand for AI continues to accelerate. Workloads are getting larger, models are becoming more complex, and there is mounting pressure to deploy AI compute... [Next page]()