Explore the innovative Text to Speech feature of the Kindle 3 in our latest video! Discover how this function transforms your ...

"VibeVoice is a novel framework designed for generating expressive, long-form, multi-speaker conversational audio, such as podcasts, from text. It addresses significant challenges in traditional ...

Microsoft’s VibeVoice is an open-source text-to-speech model for podcast-length, multi-speaker audio that captures the ...

The future wave of innovation will likely be concerned with personalization, enabling readers to personalize the voice, tempo ...

Text-to-speech with feeling - this new AI model does everything but shed a tear ElevenLabs' 'most expressive' v3 model can speak with a huge range of emotions in more than 70 languages.

ElevenLabs, the highly-valued AI voice cloning and generation startup from former Palantir alumni, today launched Scribe v1, a new speech-to-text model that reportedly achieves the highest ...

AI text-to-speech programs could “unlearn” how to imitate certain people New research shows models can be directly edited to hide selected voices, even when users specifically ask for them.

Google is enhancing Gemini's text-to-speech (TTS). On Tuesday at Google I/O 2025, the company previewed a new TTS feature, built on native audio output, that can "converse in more expressive ways ...

OpenAI unveils cutting-edge speech-to-text audio AI models API to help developers build accurate, reliable, and engaging voice-driven apps ...

Tens of trillions of language tokens Unlike traditional text-to-speech systems that rely on limited speech datasets, Octave TTS is built on an LLM trained on tens of trillions of language tokens.