AI news story
Supertone Releases Supertonic v3: On-Device Text-to-Speech Model with 31-Language Support, Fewer Reading Failures, and Expression Tags
The Seoul-based speech AI company ships its third generation of its on-device TTS engine, adding expressive tags, improved reading stability, and a 6× increase in language coverage — all while keeping the inference contract unchanged for existing int
Editor's take
Supertone's Supertonic v3 now offers 31 languages for on-device text-to-speech, incorporating expressive tags and improved reading accuracy without altering its inference contract. This expansion is significant for a market increasingly demanding localized and nuanced AI experiences, particularly as edge AI adoption grows within consumer electronics and automotive sectors seeking privacy-preserving, real-time voice capabilities.
The leap in language support, from an unspecified previous number to 31, positions Supertonic v3 to compete more effectively against established players like Amazon Polly or Google Cloud TTS, especially in regions where on-device processing is prioritized. The inclusion of expressive tags, a feature already present in some cloud-based models, brings a layer of emotional depth previously difficult to achieve on resource-constrained devices.
Future developments to monitor include the actual performance metrics of Supertonic v3 across its expanded language set and diverse hardware configurations, particularly concerning latency and power consumption. The company's ability to maintain its inference contract while scaling to 31 languages will be a key indicator of its engineering efficiency and a crucial factor for developers considering integration.
Signal score: 5
This event was corroborated by 21 independent sources. The signal score weighs cross-source corroboration, recency, source weight and topic salience. How we rank stories.
Original reporting
This story summarises reporting published by MarkTechPost. Read the original article at MarkTechPost.