OuteTTS-0.1-350M
OuteTTS-0.1-350M is an innovative text-to-speech synthesis model that employs a pure language modeling approach, avoiding the need for external adapters or complex architectures. Built on the LLaMa framework and using the Oute3-350M-DEV base model, it demonstrates that high-quality speech synthesis can be achieved through a simple method using crafted prompts and audio tokens.
Related Blueprints
This blueprint demonstrates how you can use open-source models & tools to convert input documents into a podcast featuring two speakers.
Related content
Try other existing open source solutions to create your own podcasts.
Try these prompts to create fun podcasts in the style of different personalities.
Transform newsletters, study notes, or museum guides into engaging audio episodes for quicker and more enjoyable learning.