This post was originally published on this site

Since the launch of AWS Graviton processors in 2018, we have continued to innovate and deliver improved performance for our customers’ cloud workloads. Following the success of our Graviton3-based instances, we are excited to announce three new Amazon Elastic Compute Cloud (Amazon EC2) instance families powered by AWS Graviton4 processors with NVMe-based SSD local storage: compute optimized (C8gd), general purpose (M8gd), and memory optimized (R8gd) instances. These instances deliver up to 30% better compute performance, 40% higher performance for I/O intensive database workloads, and up to 20% faster query results for I/O intensive real-time data analytics than comparable AWS Graviton3-based instances.

Let’s look at some of the improvements that are now available in our new instances. These instances offer larger instance sizes with up to 3x more vCPUs (up to 192 vCPUs), 3x the memory (up to 1.5 TiB), 3x the local storage (up to 11.4TB of NVMe SSD storage), 75% higher memory bandwidth, and 2x more L2 cache compared to their Graviton3-based predecessors. These features help you to process larger amounts of data, scale up your workloads, improve time to results, and lower your total cost of ownership (TCO). These instances also offer up to 50 Gbps network bandwidth and up to 40 Gbps Amazon Elastic Block Store (Amazon EBS) bandwidth, a significant improvement over Graviton3-based instances. Additionally, you can now adjust the network and Amazon EBS bandwidth on these instances by up to 25% using EC2 instance bandwidth weighting configuration, providing you greater flexibility with the allocation of your bandwidth resources to better optimize your workloads.

Built on AWS Graviton4, these instances are great for storage intensive Linux-based workloads including containerized and micro-services-based applications built using Amazon Elastic Kubernetes Service (Amazon EKS), Amazon Elastic Container Service (Amazon ECS), Amazon Elastic Container Registry (Amazon ECR), Kubernetes, and Docker, as well as applications written in popular programming languages such as C/C++, Rust, Go, Java, Python, .NET Core, Node.js, Ruby, and PHP. AWS Graviton4 processors are up to 30% faster for web applications, 40% faster for databases, and 45% faster for large Java applications than AWS Graviton3 processors.

Instance specifications

These instances also offer two bare metal sizes (metal-24xl and metal-48xl), allowing you to right size your instances and deploy workloads that benefit from direct access to physical resources. Additionally, these instances are built on the AWS Nitro System, which offloads CPU virtualization, storage, and networking functions to dedicated hardware and software to enhance the performance and security of your workloads. In addition, Graviton4 processors offer you enhanced security by fully encrypting all high-speed physical hardware interfaces.

The instances are available in 10 sizes per family, as well as two bare metal configurations each:

Instance Name	vCPUs	Memory (GiB) (C/M/R)	Storage (GB)	Network Bandwidth (Gbps)	EBS Bandwidth (Gbps)
medium	1	2/4/8*	1 x 59	Up to 12.5	Up to 10
large	2	4/8/16*	1 x 118	Up to 12.5	Up to 10
xlarge	4	8/16/32*	1 x 237	Up to 12.5	Up to 10
2xlarge	8	16/32/64*	1 x 474	Up to 15	Up to 10
4xlarge	16	32/64/128*	1 x 950	Up to 15	Up to 10
8xlarge	32	64/128/256*	1 x 1900	15	10
12xlarge	48	96/192/384*	3 x 950	22.5	15
16xlarge	64	128/256/512*	2 x 1900	30	20
24xlarge	96	192/384/768*	3 x 1900	40	30
48xlarge	192	384/768/1536*	6 x 1900	50	40
metal-24xl	96	192/384/768*	3 x 1900	40	30
metal-48xl	192	384/768/1536*	6 x 1900	50	40

*Memory values are for C8gd/M8gd/R8gd respectively

Availability and pricing

M8gd, C8gd, and R8gd instances are available today in US East (N. Virginia, Ohio) and US West (Oregon) Regions. These instances can be purchased as On-Demand instances, Savings Plans, Spot instances, or as Dedicated instances or Dedicated hosts.

Get started today

You can launch M8gd, C8gd and R8gd instances today in the supported Regions through the AWS Management Console, AWS Command Line Interface (AWS CLI), or AWS SDKs. To learn more, check out the collection of Graviton resources to help you start migrating your applications to Graviton instance types. You can also visit the Graviton Getting Started Guide to begin your Graviton adoption journey.

— Micah;

---

How is the News Blog doing? Take this 1 minute survey!

(This survey is hosted by an external company. AWS handles your information as described in the AWS Privacy Notice. AWS will own the data gathered via this survey and will not share the information collected with survey respondents.)

This post was originally published on this site

At re:Invent 2023, we introduced Amazon S3 Express One Zone, a high-performance, single-Availability Zone (AZ) storage class purpose-built to deliver consistent single-digit millisecond data access for your most frequently accessed data and latency-sensitive applications.

S3 Express One Zone delivers data access speed up to 10 times faster than S3 Standard, and it can support up to 2 million GET transactions per second (TPS) and up to 200,000 PUT TPS per directory bucket. This makes it ideal for performance-intensive workloads such as interactive data analytics, data streaming, media rendering and transcoding, high performance computing (HPC), and AI/ML trainings. Using S3 Express One Zone, customers like Fundrise, Aura, Lyrebird, Vivian Health, and Fetch improved the performance and reduced the costs of their data-intensive workloads.

Since launch, we’ve introduced a number of features for our customers using S3 Express One Zone. For example, S3 Express One Zone started to support object expiration using S3 Lifecycle to expire objects based on age to help you automatically optimize storage costs. In addition, your log-processing or media-broadcasting applications can directly append new data to the end of existing objects and then immediately read the object, all within S3 Express One Zone.

Today we’re announcing that, effective April 10, 2025, S3 Express One Zone has reduced storage prices by 31 percent, PUT request prices by 55 percent, and GET request prices by 85 percent. In addition, S3 Express One Zone has reduced the per-GB charges for data uploads and retrievals by 60 percent, and these charges now apply to all bytes transferred rather than just portions of requests greater than 512 KB.

Here is a price reduction table in the US East (N. Virginia) Region:

Price	Previous	New	Price reduction
Storage (per GB-Month)	$0.16	$0.11	31%
Writes (PUT requests)	$0.0025 per 1,000 requests up to 512 KB	$0.00113 per 1,000 requests	55%
Reads (GET requests)	$0.0002 per 1,000 requests up to 512 KB	$0.00003 per 1,000 requests	85%
Data upload (per GB)	$0.008	$0.0032	60%
Data retrievals (per GB)	$0.0015	$0.0006	60%

For S3 Express One Zone pricing examples, go to the S3 billing FAQs or use the AWS Pricing Calculator.

These pricing reductions apply to S3 Express One Zone in all AWS Regions where the storage class is available: US East (N. Virginia), US East (Ohio), US West (Oregon), Asia Pacific (Mumbai), Asia Pacific (Tokyo), Europe (Ireland), and Europe (Stockholm) Regions. To learn more, visit the Amazon S3 pricing page and S3 Express One Zone in the AWS Documentation.

Give S3 Express One Zone a try in the S3 console today and send feedback to AWS re:Post for Amazon S3 or through your usual AWS Support contacts.

— Channy

This post was originally published on this site

Voice interfaces are essential to enhance customer experience in different areas such as customer support call automation, gaming, interactive education, and language learning. However, there are challenges when building voice-enabled applications.

Traditional approaches in building voice-enabled applications require complex orchestration of multiple models, such as speech recognition to convert speech to text, language models to understand and generate responses, and text-to-speech to convert text back to audio.

This fragmented approach not only increases development complexity but also fails to preserve crucial linguistic context such as tone, prosody, and speaking style that are essential for natural conversations. This can affect conversational AI applications that need low latency and nuanced understanding of verbal and non-verbal cues for fluid dialog handling and natural turn-taking.

To streamline the implementation of speech-enabled applications, today we are introducing Amazon Nova Sonic, the newest addition to the Amazon Nova family of foundation models (FMs) available in Amazon Bedrock.

Amazon Nova Sonic unifies speech understanding and generation into a single model that developers can use to create natural, human-like conversational AI experiences with low latency and industry-leading price performance. This integrated approach streamlines development and reduces complexity when building conversational applications.

Its unified model architecture delivers expressive speech generation and real-time text transcription without requiring a separate model. The result is an adaptive speech response that dynamically adjusts its delivery based on prosody, such as pace and timbre, of input speech.

When using Amazon Nova Sonic, developers have access to function calling (also known as tool use) and agentic workflows to interact with external services and APIs and perform tasks in the customer’s environment, including knowledge grounding with enterprise data using Retrieval-Augmented Generation.

At launch, Amazon Nova Sonic provides robust speech understanding for American and British English across various speaking styles and acoustic conditions, with additional languages coming soon.

Amazon Nova Sonic is developed with responsible AI at the forefront of innovation, featuring built-in protections for content moderation and watermarking.

Amazon Nova Sonic in action
The scenario for this demo is a contact center in the telecommunication industry. A customer reaches out to improve their subscription plan, and Amazon Nova Sonic handles the conversation.

With tool use, the model can interact with other systems and use agentic RAG with Amazon Bedrock Knowledge Bases to gather updated, customer-specific information such as account details, subscription plans, and pricing info.

The demo shows streaming transcription of speech input and displays streaming speech responses as text. The sentiment of the conversation is displayed in two ways: a time chart illustrating how it evolves, and a pie chart representing the overall distribution. There’s also an AI insights section providing contextual tips for a call center agent. Other interesting metrics shown in the web interface are the overall talk time distribution between the customer and the agent, and the average response time.

During the conversation with the support agent, you can observe through the metrics and hear in the voices how customer sentiment improves.

The video includes an example of how Amazon Nova Sonic handles interruptions smoothly, stopping to listen and then continuing the conversation in a natural way.

Now, let’s explore how you can integrate voice capabilities in your applications.

Using Amazon Nova Sonic
To get started with Amazon Nova Sonic, you first need to toggle model access in the Amazon Bedrock console, similar to how you would enable other FMs. Navigate to the Model access section of the navigation pane, find Amazon Nova Sonic under the Amazon models, and enable it for your account.

Amazon Bedrock provides a new bidirectional streaming API (InvokeModelWithBidirectionalStream) to help you implement real-time, low-latency conversational experiences on top of the HTTP/2 protocol. With this API, you can stream audio input to the model and receive audio output in real time, so that the conversation flows naturally.

You can use Amazon Nova Sonic with the new API with this model ID: amazon.nova-sonic-v1:0

After the session initialization, where you can configure inference parameters, the model operate through an event-driven architecture on both the input and output streams.

There are three key event types in the input stream:

System prompt – To set the overall system prompt for the conversation

Audio input streaming – To process continuous audio input in real-time

Tool result handling – To send the result of tool use calls back to the model (after tool use is requested in the output events)

Similarly, there are three groups of events in the output streams:

Automatic speech recognition (ASR) streaming – Speech-to-text transcript is generated, containing the result of realtime speech recognition.

Tool use handling – If there are a tool use events, they need to be handled using the information provided here, and the results sent back as input events.

Audio output streaming – To play output audio in real-time, a buffer is needed, because Amazon Nova Sonic model generates audio faster than real-time playback.

You can find examples of using Amazon Nova Sonic in the Amazon Nova model cookbook repository.

Prompt engineering for speech
When crafting prompts for Amazon Nova Sonic, your prompts should optimize content for auditory comprehension rather than visual reading, focusing on conversational flow and clarity when heard rather than seen.

When defining roles for your assistant, focus on conversational attributes (such as warm, patient, concise) rather than text-oriented attributes (detailed, comprehensive, systematic). A good baseline system prompt might be:

You are a friend. The user and you will engage in a spoken dialog exchanging the transcripts of a natural real-time conversation. Keep your responses short, generally two or three sentences for chatty scenarios.

More generally, when creating prompts for speech models, avoid requesting visual formatting (such as bullet points, tables, or code blocks), voice characteristic modifications (accent, age, or singing), or sound effects.

Things to know
Amazon Nova Sonic is available today in the US East (N. Virginia) AWS Region. Visit Amazon Bedrock pricing to see the pricing models.

Amazon Nova Sonic can understand speech in different speaking styles and generates speech in expressive voices, including both masculine-sounding and feminine-sounding voices, in different English accents, including American and British. Support for additional languages will be coming soon.

Amazon Nova Sonic handles user interruptions gracefully without dropping the conversational context and is robust to background noise. The model supports a context window of 32K tokens for audio with a rolling window to handle longer conversations and has a default session limit of 8 minutes.

The following AWS SDKs support the new bidirectional streaming API:

• AWS SDK for C++
• AWS SDK for Java
• AWS SDK for JavaScript
• AWS SDK for Kotlin
• AWS SDK for Ruby
• AWS SDK for Rust
• AWS SDK for Swift

Python developers can use this new experimental SDK that makes it easier to use the bidirectional streaming capabilities of Amazon Nova Sonic. We’re working to add support to the other AWS SDKs.

I’d like to thank Reilly Manton and Chad Hendren, who set up the demo with the contact center in the telecommunication industry, and Anuj Jauhari, who helped me understand the rich landscape in which speech-to-speech models are being deployed.

To learn more, these articles that enter into the details of how to use the new bidirectional streaming API with compelling demos:

• Build Your Own AI Podcast Co-Host: Step-by-Step with Amazon Q CLI and Amazon Nova Sonic
• Speech-to-Speech AI: From Dr. Sbaitso to Amazon Nova Sonic

Whether you’re creating customer service solutions, language learning applications, or other conversational experiences, Amazon Nova Sonic provides the foundation for natural, engaging voice interactions. To get started, visit the Amazon Bedrock console today. To learn more, visit the Amazon Nova section of the user guide.

– Danilo

---

How is the News Blog doing? Take this 1 minute survey!

(This survey is hosted by an external company. AWS handles your information as described in the AWS Privacy Notice. AWS will own the data gathered via this survey and will not share the information collected with survey respondents.)