Back to All
Developer Blog

Cartesia brings Voice AI to Googlebook with Snapdragon X Series

Sign up for Developer monthly newsletter-image

Sign up for Developer monthly newsletter

Join thousands of developers around the globe who receive latest news and updates from our monthly curated newsletter.

Sign up
Come for support, stay for the community-image

Come for support, stay for the community

Get support from experts, connect with like-minded developers, and access exclusive virtual events.

Join Developer Discord

Cartesia is bringing a new wave of NPU-accelerated, human-like voice AI experiences to Googlebook. Cartesia designed new model architectures for the Qualcomm Hexagon NPU, bringing full on-device voice through both speech generation and transcription. Running locally on Googlebooks with Snapdragon X Series processors, these experiences can enable lower latency, greater privacy, and reduced cloud dependency.

Cartesia: Real-Time AI Speech Generation on the Qualcomm Hexagon NPU

Voice is rapidly becoming the primary interfaces for AI. Whether interacting with an AI assistant, engaging with a conversational agent, or consuming narrated content, users expect speech that sounds natural and responds instantly. Meeting both bars on-device has been historically difficult.

Cartesia is bringing this capability to Googlebook through its
Sonic text-to-speech and Ink speech-to-text models, optimized for real-time conversational AI experiences. Powered by a new class of efficient architectures designed for low-latency deployment, Cartesia enables high-quality voice generation directly on device, where memory and power are tightly constrained.

Rather than adapting cloud-scale transformers to run on edge hardware, Cartesia designed the first set of these alternative architectures directly around the Hexagon NPU. 

By running the full end-to-end pipeline on the Hexagon NPU, Cartesia delivers human naturalness and latency below the threshold of human perception (less than 100ms) to power:

  • Real-time voice agents and AI assistants

  • Personalized narration and reading experiences

  • Accessibility-focused speech applications

  • Interactive learning and educational experiences

  • AI companions and conversational interfaces

Running inference locally enables speech experiences that are more responsive while minimizing dependence on cloud-based processing.

Expanding Snapdragon Mobile Innovation to Googlebook

Cartesia has already invested in optimizing voice AI experiences for mobile devices powered by Snapdragon. As they expand their offerings to Googlebook, they can take advantage of the same AI acceleration technologies that have enabled high-performance AI experiences across the Snapdragon ecosystem.

This creates a natural path for developers to extend AI innovations across multiple form factors while continuing to benefit from:

  • Hexagon NPU acceleration

  • Consistent AI performance

  • Low-latency user experiences

  • Power-efficient AI execution

  • Privacy-first on-device intelligence

For developers, this means building compelling AI experiences that scale across devices. For users, it means immediate access to powerful AI capabilities directly from Google Play Store.

Building the Future of Voice AI

Qualcomm Technologies' collaboration with Cartesia highlights the growing momentum behind on-device AI and demonstrate how the Hexagon NPU can enable entirely new categories of voice experiences on Googlebooks.

With applications from Cartesia coming soon to Google Play, Googlebook users will gain access to powerful voice-first AI experiences that are fast, private, and powered by the Hexagon NPU.

As the voice AI ecosystem continues to grow, Snapdragon X Series and the Hexagon NPU are helping bring the next generation of intelligent, conversational, and personalized experiences directly to users, wherever they are.

Opinions expressed in the content posted here are the personal opinions of the original authors, and do not necessarily reflect those of Qualcomm Incorporated or its subsidiaries ("Qualcomm"). The content is provided for informational purposes only and is not meant to be an endorsement or representation by Qualcomm or any other party. This site may also provide links or references to non-Qualcomm sites and resources. Qualcomm makes no representations, warranties, or other commitments whatsoever about any non-Qualcomm sites or third-party resources that may be referenced, accessible from, or linked to this site.

Snapdragon and Qualcomm branded products are products of Qualcomm Technologies, Inc. and/or its subsidiaries.

About the Author
Devang Aggarwal
Devang AggarwalProduct Manager, Senior

© Qualcomm Technologies, Inc. and/or its affiliated companies.

Snapdragon and Qualcomm branded products are products of Qualcomm Technologies, Inc. and/or its subsidiaries. Qualcomm patents are licensed by Qualcomm Incorporated.

Note: Certain services and materials may require you to accept additional terms and conditions before accessing or using those items.

References to "Qualcomm" may mean Qualcomm Incorporated, or subsidiaries or business units within the Qualcomm corporate structure, as applicable.

Qualcomm Incorporated includes our licensing business, QTL, and the vast majority of our patent portfolio. Qualcomm Technologies, Inc., a subsidiary of Qualcomm Incorporated, operates, along with its subsidiaries, substantially all of our engineering, research and development functions, and substantially all of our products and services businesses, including our QCT semiconductor business.

Materials that are as of a specific date, including but not limited to press releases, presentations, blog posts and webcasts, may have been superseded by subsequent events or disclosures.

Nothing in these materials is an offer to sell or license any of the services or materials referenced herein.