Search Results for "xtream-codes"

...Built on an RVQ Transformer architecture inspired by Sesame CSM, it combines a powerful Llama-based backbone with an autoregressive audio decoder to produce high-quality audio from text. The model supports both standard speech synthesis and voice-conditioned generation using optional audio prompts for voice cloning. Miso TTS generates Mimi audio codes and can leverage conversation history to create more contextually aware and realistic dialogue. Designed for local deployment, it offers watermarking by default to help promote responsible use of generated audio. With its focus on emotive speech generation, Miso TTS delivers state-of-the-art performance for AI voice applications, virtual assistants, and conversational AI experiences.

The CSM (Conversational Speech Model) is a speech generation model developed by Sesame AI that creates RVQ audio codes from text and audio inputs. It uses a Llama backbone and a smaller audio decoder to produce audio codes for realistic speech synthesis. The model has been fine-tuned for interactive voice demos and is hosted on platforms like Hugging Face for testing. CSM offers a flexible setup and is compatible with CUDA-enabled GPUs for efficient execution.

We introduce a language modeling approach for text to speech synthesis (TTS). Specifically, we train a neural codec language model (called VALL-E) using discrete codes derived from an off-the-shelf neural audio codec model, and regard TTS as a conditional language modeling task rather than continuous signal regression as in previous work. During the pre-training stage, we scale up the TTS training data to 60K hours of English speech which is hundreds of times larger than existing systems. VALL-E emerges in-context learning capabilities and can be used to synthesize high-quality personalized speech with only a 3-second enrolled recording of an unseen speaker as an acoustic prompt. ...