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 ...

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.

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 ...

I finally found an Android voice typing app that makes dictation effortless

Wispr Flow finally fixes voice typing on Android ...

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 ...