Kitten TTS 2 on BestTTS

A BestTTS reference page for KittenML's 1.7B ternary speech model

BestTTS's model page for Kitten TTS 2 from KittenML: a 1.7-billion-parameter speech language model with ternary transformer weights, reference voice cloning from a 5–30 second sample, 123 voices and 16 languages with named voices on its model card, CPU execution (incl. a C++ runtime), setup steps and Stellon Labs Community License terms. BestTTS is a free directory and does not provide the model.

Category: Music & Audio. Pricing: free. Visit website

Alternatives to Kitten TTS 2 on BestTTS in Music & Audio

• Deepgram — Power enterprise voice solutions with Deepgram’s Speech-to-Text, Text-to-Speech, and Voice Agent APIs. Real-time, accur…
• CapCut — CapCut is an AI-powered, all-in-one creative platform that offers video editing and image design capabilities. It’s ava…
• ACE-Step — Open-source foundation model for state-of-the-art music generation
• BestTTS — Find, compare and hear the best text-to-speech models
• Vocal Separator — Separate vocals and prepare music for practice.
• MusicAura AI — AI Music Generator for Every Mood | Musicaura