The latest AI news and updates of Cartesia — Voice AI company building real-time speech models for live, human-like voice agents. Covering Cartesia's latest product updates, analysis, and launches from the past 90 days.
CartesiaOct 15Cartesia's Sonic 3.6 text-to-speech model secured the top ranking across six Indic languages on Deccan AI's new VoxClash TTS 2.0 leaderboard. The benchmark evaluated 16 models head-to-head using native-speaker raters and real-world use cases. Sonic 3.6 achieved the highest Elo scores for Bengali, Malayalam, Marathi, Telugu, Hindi, and Gujarati.
CartesiaOct 12Cartesia is partnering with Raise Financial Services to provide multilingual voice models for Indian financial platforms. Cartesia’s models currently power conversational KYC on the Dhan trading platform, where over 75% of interactions occur in non-English languages. Additionally, Raise’s voice agents handle more than one-third of calls outside business hours without human intervention, with plans to scale across group entities.
CartesiaSep 24Cartesia launched Multilingual Voices, with 50+ library voices now speaking up to 25 languages natively. The update adds one-click multilingual support for custom voice clones. These models maintain consistent identity, including pitch and texture, across different languages for global voice agent deployments.
CartesiaSep 15Cartesia published an analysis of text-to-speech evaluation, arguing that quality is multidimensional and cannot be captured by a single leaderboard number. The post details how metrics like Word Error Rate saturate, while automated quality predictors often miss nuanced failures like pitch accent or streaming glitches. Effective evaluation requires testing models against specific product contexts, languages, and use cases.
CartesiaSep 2Cartesia's Sonic-3.6 model ranks first across all eight customer support categories on Datapoint AI's newly released TTS benchmark. The ranking, based on 42,000 blind human votes, evaluates performance in areas including empathy, spell-outs, repairs, and disfluency. The benchmark uses the largest open-source human audio preferences dataset to measure model quality.
CartesiaAug 29Cartesia released Sonic-3.6, a text-to-speech model rebuilt from the architecture up to replace its previous version. The model achieves up to 93% listener preference in blind head-to-head tests across fifteen locales. It supports 44 languages, generates audio twice as fast as its predecessor, and delivers sub-90ms latency for real-time voice agent applications.
CartesiaAug 22Cartesia launched Sonic-3.6 in beta, featuring improved naturalness across 44 languages. The model ranks #1 on Artificial Analysis’ provider and controlled voice streaming leaderboards. It supports seamless Hinglish code-switching between Hindi and English, with fundamental model improvements derived from developer feedback.
CartesiaAug 15Cartesia released Sonic 3.6, enhancing naturalness and accuracy across nine existing Indic languages. The update refines Hindi flow and Hinglish code-switching while adding support for Urdu and Odia. These improvements provide more expressive and accurate voice generation tailored to India's diverse linguistic landscape.
CartesiaAug 13Cartesia integrated HeyGen’s LiveAvatar with its Line agent platform, enabling real-time, lip-synced video avatars for voice agents. The Cartesia Agent Connector bridges the agent’s audio output with the avatar’s visual rendering. This integration is available via the web app or API, allowing agents to maintain their existing prompt, tool access, and turn-taking logic.
CartesiaAug 11Cartesia updated its Ink-2 speech-to-text model with keyterm prompting and configurable turn detection. Keyterm prompting accepts rare domain-specific terms — product names, jargon, and foreign words — boosting keyword recall by 20% with zero added latency. Configurable turn detection enables endpointing tuned to prioritize either lower latency or higher accuracy for specific conversational flows.
Frequently asked questions