Alibaba’s Marco-Voice pairs voice cloning with controllable emotion for more natural and expressive synthetic speech in ...

On September 18, Mianbi Intelligent released the VoxCPM voice generation base model with 0.5 billion parameters. This model ...

Kokoro 82M is a lightweight yet powerful text-to-speech (TTS) model designed for local use. Unlike many cloud-based TTS solutions, Kokoro 82M operates entirely offline, making sure both privacy and ...

Researchers at Amazon have trained the largest ever text-to-speech model yet, which they claim exhibits "emergent" qualities improving its ability to speak even complex sentences naturally. The ...

OpenAI has today introduced a suite of advanced audio models and tools through its API, designed to empower developers in creating sophisticated, voice-driven applications. These updates include ...

Want smarter insights in your inbox? Sign up for our weekly newsletters to get only what matters to enterprise AI, data, and security leaders. Subscribe Now Groq and PlayAI announced a partnership ...

SAN FRANCISCO--(BUSINESS WIRE)--Deepgram, the leading voice AI platform for enterprise use cases, today announced Aura-2, its next-generation text-to-speech (TTS) model purpose-built for real-time ...

With the widespread application of voice interfaces, artificial intelligence systems not only need to process spoken language ...

The ' Play 3.0 mini ' has been released, which supports over 30 languages and can read text in multiple voices and accents. It also supports Japanese, and its selling point is the 'naturalness of the ...

The new medical model delivers 50% fewer keyword errors on clinical terms and 17% lower overall word errors than the next ...