Higgs Audio v2 by BosonAI is a powerful open-source audio foundation model. It excels at generating expressive, multi-speaker dialogues and long-form audio. It outperforms GPT-4o-mini-tts on emotion benchmarks and is now available for developers.

Higgs Audio, from Boson AI, is the advanced AI for audio understanding & generation. LLM-based models deliver context-aware, expressive speech & deep understanding. Outperforms key benchmarks.