Fetching from the wire…
Public story · 2026-03-20 · source-backed
KittenML released three TTS models on GitHub (432 points, 160 comments on HN — highest point total in today's data) with the smallest under 25MB, enabling full on-device inference without cloud round-trips. Targets mobile and edge where existing TTS models are too large. The velocity signals strong demand for lightweight, deployable voice models outside the API tier.
Each link below shares sources, entities, or timing with this story.
KittenML released KittenTTS / Shared entities / Same source / Earlier coverage
Linked by a graph relationship (KittenML released KittenTTS); both cover KittenML, KittenTTS; cite the same source (KittenML released three TTS models).
Linked by a graph relationship (KittenML released KittenTTS); both cover KittenML, KittenTTS; cite the same source (KittenML released three TTS models).
Shared entity: GitHub / Same source domain / Shared topic / What happened next
Both cover GitHub; reported by the same outlet (github.com); overlapping topics (cloud, data, model).
Both cover GitHub; reported by the same outlet (github.com); overlapping topics (cloud, full, model).
Shared entities / Same source domain / What happened next
Both cover GitHub, TTS; reported by the same outlet (github.com); picks up the GitHub thread on 2026-08-12.
Both cover GitHub, TTS; reported by the same outlet (github.com); picks up the GitHub thread on 2026-07-28.
Shared entity: GitHub / Same source domain / Shared topic / Earlier coverage
Both cover GitHub; reported by the same outlet (github.com); overlapping topics (inference, model, point).
Shared entity: GitHub / Same source domain / Shared topic / What happened next
Both cover GitHub; reported by the same outlet (github.com); overlapping topics (comment, point).