A 2013 Intel CPU nearly ties an M2 Pro at local text-to-speech, no GPU (ariya.io)
Kokoro packs roughly 50 voices into 82M parameters, from a developer who goes by Hexgrad. The post wires it up as a container with an OpenAI-compatible API, so a local LLM can hand off its text and get audio back without renting a cloud voice.
The thread reads less like a debate than a deployment log: a door intercom, Home Assistant over Sonos speakers, epub audiobooks, a Japanese-tutor app. The asterisk comes from someone shipping it in an accessibility product — ask Kokoro to say just 'six' and it blurts 'ah-six-ah'.
Sign in to save