This is slower and more resource intensive than most TTS models so keep that in mind. But I do get more expressive results. You can voice clone or create a custom voice but I find voice cloning works much better. I had an issue with auto downloading I downloaded  from <a target="_blank" rel="ugc" href="https://huggingface.co/ResembleAI/Dramabox/tree/main">https://huggingface.co/ResembleAI/Dramabox/tree/main</a> within /models make a folder called drama box download <a target="_blank" rel="ugc" href="https://huggingface.co/ResembleAI/Dramabox/blob/main/dramabox-audio-components.safetensors">dramabox-audio-components.safetensors</a><a target="_blank" rel="ugc" href="https://huggingface.co/ResembleAI/Dramabox/blob/main/dramabox-dit-v1.safetensors">dramabox-dit-v1.safetensors</a>And from the assets folder download <a target="_blank" rel="ugc" href="https://huggingface.co/ResembleAI/Dramabox/blob/main/assets/silence_latent_frame.pt">silence_latent_</a><a target="_blank" rel="ugc" href="http://frame.pt">frame.pt</a> This is slower and more resource intensive than most TTS models so keep that in mind. But I do get more expressive results.

Files with SHA256: 5e7da76c892a4c65adcd058ae9f1d5e0f3b887bf7b0b2f153c6427d9f999c303