AIHacker Noonabout 3 hours ago
The Higgs-tts-2-3b-base Model: A Text-to-Speech Foundation Model
1 min read
BosonAI released Higgs-TTS-2-3B-base, a text-to-speech foundation model with 5.8 billion total parameters. It uses a 3.6B Llama-3.2-3B backbone and a 2.2B DualFFN audio adapter. The adapter operates at the same training and inference cost as the base LLM.
Level
Hype check
Tap to vote and see what everyone thinks.
