Scholarlink

The surge in global podcast and story listeners, now totaling 504.9 million and comprising 23.5% of internet users, highlights the growing demand for advanced narrative tools. This study explores the transformative potential of voice in storytelling by developing a deep learning model designed to generate diverse narratives based on user prompts. Utilizing advanced voice cloning techniques, the model aims to embed nuanced emotions within these narratives, merging human emotion with technological capabilities to create a sustainable tool for enhancing individual well-being. The model was constructed using PyTorch, TensorFlow, and Convolutional Neural Networks (CNN), with voice cloning powered by BARK, an open-source transformer-based model. Audioverse promises to significantly enrich human connections and revolutionize the storytelling landscape.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Audioverse: Personalized Story-Telling Using Voice Cloning

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Kasey Ann Britto,
  • J. Harini,
  • M. Shivanii,
  • Pranavi Karthik,
  • B. N. Kalpana,
  • M. Karthi

摘要

The surge in global podcast and story listeners, now totaling 504.9 million and comprising 23.5% of internet users, highlights the growing demand for advanced narrative tools. This study explores the transformative potential of voice in storytelling by developing a deep learning model designed to generate diverse narratives based on user prompts. Utilizing advanced voice cloning techniques, the model aims to embed nuanced emotions within these narratives, merging human emotion with technological capabilities to create a sustainable tool for enhancing individual well-being. The model was constructed using PyTorch, TensorFlow, and Convolutional Neural Networks (CNN), with voice cloning powered by BARK, an open-source transformer-based model. Audioverse promises to significantly enrich human connections and revolutionize the storytelling landscape.