iCreatAI News
Skip to content
Hacker News AI· Hasitron·· 2 days agoAI score69

Haru-4B: A voice AI that can listen and speak at the same time

Haru-4B: A voice AI that can listen and speak at the same time

AI summary

Haru-4B is a full-duplex continuous spoken dialogue foundation model built on Qwen3.5-4B that processes incoming and outgoing speech simultaneously at 7.5 Hz, with about 65 ms end-to-end latency on a MacBook. It was pretrained on over 40 million hours of real speech across more than 160 languages, excluding LLM-generated and TTS-synthesized dialogues, and uses 64-dimensional continuous acoustic latents with single-step MeanFlow generation. Model weights are on Hugging Face and code on GitHub, released as a pretrained base model for further fine-tuning and research.

Source: Hacker News AI · blog.higurashi.ai