Qwen TTS Ships Local TTS Under Apache 2.0 : Voice Cloning in 3 Seconds

Qwen TTS focuses on on-device processing with no external API; emotion control relies on precise prompts, shaping output ...
IEEE

An Automated Method to Correct Artifacts in Neural Text-to-Speech Models

Abstract: Recent advances in deep learning technology have enabled high-quality speech synthesis, and text-to-speech models are widely used in a variety of applications. However, even state-of-the-art ...

How Large Scale Speech Models Will Impact Voice AI

A duplex speech-to-speech model changes the premise: The intelligence layer consumes audio and produces audio directly. The model can attend to what was said and how it was said—content and delivery ...

Tom Pelphrey Takes on Task of Playing the Most Famous Man to Ever Live — Jesus Christ (Exclusive)

The Emmy nominee segues from ‘Task’ to ‘The Christ,’ a Faith Radio Network podcast starring Pelphrey as Jesus alongside David ...

KittenTTS Nano AI Small Text-to-Speech LLM Runs on CPUs Without a GPU

KittenTTS brings small text to speech models to edge devices; the Nano 8-bit model is about 25 MB, local playback is possible.