PulseAugur
EN
LIVE 22:56:01

Together AI releases Cartesia Sonic 3.5 for real-time TTS

By PulseAugur Editorial · [3 sources] ·

Together AI has announced the release of Cartesia Sonic 3.5, a new text-to-speech (TTS) model designed for real-time applications. The model boasts sub-90ms latency and supports 42 languages, with features for context-aware pronunciation and accurate transcript following. Developers can now access over 150 Cartesia Sonic 3.5 voices through Together AI's voice finder tool to compare and select voices before deployment. AI

IMPACT Enhances real-time TTS capabilities with low latency and broad language support, potentially improving voice agent interactions.

RANK_REASON Model release announcement from a frontier lab.

Read on X — Together (inference / OSS) →

AI-generated summary · Google Gemini · from 3 sources. How we write summaries →

COVERAGE [3]

  1. X — Together (inference / OSS) TIER_1 English(EN) · togethercompute ·

    Try Sonic 3.5 in voice finder: https://t.co/5L8df8yzQM

    Try Sonic 3.5 in voice finder: https://t.co/5L8df8yzQM Model page: https://t.co/0cvwZAsguA

  2. X — Together (inference / OSS) TIER_1 English(EN) · togethercompute ·

    Sonic 3.5 is built for real-time TTS where latency, pronunciation, and delivery matter.

    Sonic 3.5 is built for real-time TTS where latency, pronunciation, and delivery matter. → Sub-90ms latency → Native support for 42 languages → Accurate transcript following for codes, IDs, and structured speech → Context-aware pronunciation for words like read, bass, and bow

  3. X — Together (inference / OSS) TIER_1 English(EN) · togethercompute ·

    Cartesia Sonic 3.5 is now available on Together AI.

    Cartesia Sonic 3.5 is now available on Together AI. We added 150+ @cartesia Sonic 3.5 voices to voice finder, so developers can listen, compare, and pick the right voice for real-time agents before deploying on Together AI. https://t.co/U3dk6hcMub

RELATED ENTITIES

RELATED TOPICS