Soul App's Open-Source Model for AI Podcasts
Soul AI Lab has open-sourced its voice podcast generation model, SoulX-Podcast, designed for multi-speaker dialogue scenarios.
- Supports multiple languages and dialects, including Mandarin, English, Sichuanese, and Cantonese
- Generates natural, fluent multi-turn voice dialogues over 60 minutes long
- Achieves accurate speaker switching and rich prosodic variation
SoulX-Podcast also excels in general speech synthesis and voice cloning tasks, providing an authentic voice experience.
No additional quotes available.
Author summary: SoulX-Podcast brings human-like naturalness to AI podcasts.