#Mimi codec

'Liquid AI released LFM2-Audio-1.5B, an end-to-end audio-language model that achieves sub-100 ms latency and supports ASR, TTS and conversational agents from a compact 1.5B-parameter stack.'

'VoXtream is an open-source full-stream zero-shot TTS that begins speaking from the first word, delivering sub-120 ms first-packet latency with compiled GPUs and continuous 80 ms audio frames.'