What is Earkind?
Earkind offers a novel approach to podcasting by leveraging artificial intelligence to generate engaging and informative content. The platform combines large language models with neural expressive text-to-speech and programmatic audio editing to create complete podcast episodes, including descriptions, based on curated news and research papers.
The podcasts feature a cast of AI-generated characters, such as Giovani Pete Tizzano, Robert, Olivia, and Belinda, who engage in discussions and commentary, adding a touch of humor and personality to the listening experience. The process integrates various AI technologies, including those from Azure, to provide a unique and dynamic audio experience.
Features
- AI-Generated Content: Podcasts are created using a combination of large language models and curated news/research.
- Expressive Text-to-Speech: Utilizes advanced text-to-speech technology to create natural-sounding voices.
- Programmatic Audio Editing: Automates the audio editing process, including sound effects, music, and transitions.
- Unique AI Characters: Features a cast of AI personalities with distinct perspectives.
- Automated Description Generation: Creates podcast descriptions with timestamps and summaries using AI.
Use Cases
- Content creation for podcasters
- Automated news summarization
- Research paper analysis and discussion
- Generating unique audio content
- Personalized audio experiences
