AWS First Steps
LanguageEnglish
New feature

Announcing Amazon Nova 2.5 Sonic with improved reasoning for voice agents

Amazon Nova 2.5 Sonic, the latest speech-to-speech model for real-time voice agents, now generally available with enhanced reasoning, instruction following, and tool-calling accuracy.

We are now generally available Amazon Nova 2.5 Sonic, the latest speech recognition model for natural real-time speech agents, improving inference, instruction understanding, and tool call accuracy while reducing latency. This enables developers to build more advanced speech agents that can perform tasks like order confirmation and return initiation within conversations. Built on existing features such as robust speech understanding, expressive voice in seven languages, controllable turn-taking, mixed speech and text sessions, asynchronous tool calls, and a 256K context window, Nova 2.5 Sonic can be combined with Strands Bidi Agents to build production-ready speech agents in just a few lines of code. It is available on Amazon Bedrock in US East (N. Virginia), US West (Oregon), Europe (Stockholm), and Asia Pacific (Tokyo) regions at the same price as Nova 2 Sonic.

Why it matters

This update is relevant for developers building voice agents for customer service, personal AI assistants, and real-time conversational applications.

Read the original AWS announcement

Related articles and terms

Text-to-Speech - Natural Speech Synthesis and Multi-Language Support with Amazon PollyLearn how to implement text-to-speech (TTS) with Amazon Polly and build voice-interactive interfaces by integrating with Amazon Lex. Covers natural speech synthesis with the neural voice engine and practical multi-language support.Speech-to-Text - Building a High-Accuracy Automatic Transcription Platform with Amazon TranscribeLearn how to convert speech to text (STT) with Amazon Transcribe and build a bidirectional voice processing pipeline by combining it with Amazon Polly. Covers real-time transcription, speaker identification, and accuracy improvements with custom vocabularies.Amazon PollyA text-to-speech service that converts text into natural-sounding audioAmazon TranscribeA high-accuracy speech recognition service that automatically converts audio to textImplementing Text-to-Speech with Amazon Polly - Neural Voices and SSML Speech ControlGenerate natural-sounding speech with the Neural TTS engine and control speech rate, pitch, and pauses with SSML tags. Learn how to build diverse audio content using real-time streaming and asynchronous synthesis to S3.