bazlan··on VUI – open-source Jarvis stack with a 300M TTS ModelDefinitely possible but tricky with stacks > 1B in params
bazlan··on VibeVoice: A Frontier Open-Source Text-to-Speech ModelSad to not see vui on the comparisons!A 100M podcast modelhttps://huggingface.co/spaces/fluxions/vui-space
bazlan··on Show HN: Dia, an open-weights TTS model for generating realistic dialoguefluxions.ai has a similar model
bazlan··on Launch HN: Hamming (YC S24) – Automated Testing for Voice AgentsAs someone who has worked in TTS for over 4 years now. I can tell you that evaluation is the most difficult aspect of generative audio ML.How will this really check that the models are performing well vs just listening?