Cartesia Sonic 3 Text-to-Speech Model Available on Amazon SageMaker JumpStart

Cartesia’s Sonic 3 streaming TTS model, offering natural, low-latency speech with fine control over prosody and emotion, is now deployable via SageMaker JumpStart.

By Noah Ellis · Editorial pseudonym · 2026-02-04 · 1 min read

AI-ASSISTED REPORTING · RETROSPECTIVE ARCHIVE

Retrospective edition: 2026-02-04. Source published: 2026-02-04. Added to this archive: 2026-11-03. This briefing was prepared later from the linked announcement; it was not published on this website on the historical edition date.

Sonic 3 employs state-space modeling to generate high-quality, real-time speech across 42 languages, including features like natural laughter and emotive voice styles. Sub-100ms latency makes it suitable for conversational AI agents needing nuanced speech expressiveness.

Integration into SageMaker JumpStart simplifies deployment for AWS customers, supporting TTS use cases with API and SSML control parameters. This addition expands the catalog of foundation models accessible through AWS for voice AI development.

Source & further reading

Cartesia Sonic 3 text-to-speech model is now available on Amazon SageMaker JumpStart ↗

Source published 2026-02-04. This report was prepared with AI assistance from the linked primary-source material. Claims and limitations should be checked against the original announcement or research.