📄️ Text-to-Speech (TTS) Generation
Transformer Lab supports Text-to-Speech (TTS) on MLX (Apple Silicon), CUDA (NVIDIA GPUs), and ROCm (AMD GPUs). This feature lets you convert plain text into natural-sounding speech directly inside Transformer Lab.
📄️ Training Text-to-Speech Models
Transformer Lab allows you to train custom Text-to-Speech (TTS) models on CUDA and AMD. Fine-tune a model on your own dataset to capture a specific voice, accent, or speaking style.