Deepgram Launches Streaming Speech, Text, and Voice Agents on Amazon SageMaker AI

Innovative streaming speech solution delivers enterprise-grade speech-to-text, text-to-speech, and voice agents with sub-second latency directly through the SageMaker API LAS VEGAS – November 30, 2025 – Deepgram, the world’s most realistic and real-time Voice AI platform, today announced native integration with Amazon SageMaker AI, delivering streaming, real-time speech-to-text (STT), text-to-speech (TTS), and the Voice Agent API as Amazon SageMaker AI real-time endpoints, no custom pipelines or orchestration required. Teams can now build, deploy, and scale voice-powered applications inside their existing AWS workflows while maintaining the security and compliance benefits of their AWS environment.“Deepgram’s integration with Amazon SageMaker represents an important step forward for real-time voice AI. By bringing our streaming speech models directly into SageMaker, enterprises can deploy speech-to-text, text-to-speech, and voice agent capabilities with sub-second latency, all within their AWS environment. This collaboration extends SageMaker’s functionality and gives developers a powerful way to build and scale voice-driven applications securely and efficiently,” said Scott Stephenson, CEO and Co-Founder, Deepgram.Native streaming via Amazon SageMaker endpoints means no workarounds or hoops to jump through, just clean, real-time inferences through the SageMaker API. The integration enables sub-second latency and enterprise-grade reliability for high-scale use cases like contact centers, trading floors, and live analytics.Built to run on AWS, the solution supports streaming responses via InvokeEndpointWithResponseStream and keeps data within AWS. Customers can deploy Deepgram in their Amazon Virtual Private Cloud (Amazon VPC) or as a managed service, aligning with stringent data residency and compliance requirements.“Enterprise developers need to build voice AI applications at scale without compromising on speed, accuracy, or security," said Stephenson. "Our native integration with Amazon SageMaker removes the complexity from deploying real-time voice capabilities, allowing AWS customers to focus on innovation rather than infrastructure. By bringing our state-of-the-art speech models directly into the AWS environment where companies already operate, we're making it dramatically easier for organizations to create voice experiences that truly transform how they engage with customers and analyze conversations at scale."The integration is also backed by a strong relationship with AWS. Deepgram is an AWS Generative AI Competency Partner and has signed a multi-year Strategic Collaboration Agreement (SCA) with AWS to accelerate enterprise adoption."Deepgram's new Amazon SageMaker AI integration makes it simple for customers to bring real-time voice capabilities into their AWS workflows," said Ankur Mehrotra, general manager for Amazon SageMaker at AWS. "By offering streaming speech-to-text and text-to-speech directly through Amazon SageMaker endpoints, Deepgram helps developers accelerate innovation while maintaining data security and compliance on AWS. This integration is a great example of how Deepgram is expanding its market reach by making generative AI more accessible and powerful through AWS services, while enabling our mutual customers to build sophisticated voice applications."The integration is available to customers building on AWS, with live demonstrations planned at AWS re:Invent in Las Vegas, December 1–5, 2025, in Deepgram Booth #690. Learn more about our AWS partnership and technical implementation on Deepgram’s AWS partner page, and read the AWS blog: “Introducing bidirectional streaming for real-time inference on Amazon SageMaker AI.”About DeepgramDeepgram is the world’s most realistic and real-time Voice AI platform, offering speech-to-text (STT), text-to-speech (TTS), and full speech-to-speech (STS) capabilities–all powered by its enterprise-grade runtime. 200,000+ developers build with Deepgram’s voice-native foundational models – accessed through cloud APIs or as self-hosted / on-premises APIs – due to its unmatched accuracy, low latency, and pricing. Customers include technology ISVs building voice products or platforms, co-sell partners working with large enterprises, and enterprises solving internal use cases. Having processed over 50,000 years of audio and transcribed over 1 trillion words, there is no organization in the world that understands voice better than Deepgram. To learn more, please visit www.deepgram.com, read its developer docs, or follow @DeepgramAI on X and LinkedIn.###PR Contact:Nicole GormanGorman Communications, for DeepgramM: 508-397-0131nicolegorman@gormancommunications.com