KittenTTS: The 25MB Model That Makes On-Device TTS Finally Practical
KittenTTS ships a 15M-parameter TTS model in 25MB that runs on CPU at 1.5x realtime — no GPU, no API key, no per-character billing.
March 20, 202611 min read
Tag: on-device-ai
1 post tagged with “on-device-ai”