OpenMOSS/MOSS-TTS — 2,591 Stars

About This Repo#

OpenMOSS/MOSS-TTS — 2,591 ⭐

MOSS‑TTS Family is an open‑source speech and sound generation model family from MOSI.AI and the OpenMOSS team. It is designed for high‑fidelity, high‑expressiveness, and complex real‑world scenarios, covering stable long‑form speech, multi‑speaker dialogue, voice/character design, environmental sound effects, and real‑time streaming TTS. - OpenMOSS/MOSS-TTS

Narration#

Can a single open-source model generate speech, sound effects, and even multi-character dialogue all at once? MOSS-TTS from MOSI.AI is completely redefining what text-to-speech technology can do. This powerful model family delivers stunning high-fidelity long-form speech, natural multi-speaker conversations, custom voice and character design, rich environmental sound effects, and real-time streaming—all in one unified, production-ready system. With over twenty-five hundred GitHub stars, MOSS-TTS proves open-source voice AI can rival the very best proprietary solutions out there. Follow ForkCast for more open-source breakthroughs.

Watch#

• Video: YouTube
• Repo: GitHub