MOSS-VoiceGenerator: Create Realistic Voices with Natural Language Descriptions
This work addresses the need for more natural and controllable voice creation in applications like storytelling and conversational assistants, though it is incremental by building on existing voice design models.
The paper tackled the problem of generating realistic speaker timbres from natural language descriptions, and the result was MOSS-VoiceGenerator, which outperformed other models in subjective preference studies for overall performance, instruction-following, and naturalness.
Voice design from natural language aims to generate speaker timbres directly from free-form textual descriptions, allowing users to create voices tailored to specific roles, personalities, and emotions. Such controllable voice creation benefits a wide range of downstream applications-including storytelling, game dubbing, role-play agents, and conversational assistants, making it a significant task for modern Text-to-Speech models. However, existing models are largely trained on carefully recorded studio data, which produces speech that is clean and well-articulated, yet lacks the lived-in qualities of real human voices. To address these limitations, we present MOSS-VoiceGenerator, an open-source instruction-driven voice generation model that creates new timbres directly from natural language prompts. Motivated by the hypothesis that exposure to real-world acoustic variation produces more perceptually natural voices, we train on large-scale expressive speech data sourced from cinematic content. Subjective preference studies demonstrate its superiority in overall performance, instruction-following, and naturalness compared to other voice design models.