OpenMOSS / MOSS-TTS
MOSS TTS 1.5
Studio-grade multilingual voice synthesis
Mac and Windows
Languages
31
Output
48 kHz stereo
License
Apache 2.0
Platform
Mac + Windows
Model overview
Built into OpenVox for private local voice generation.
MOSS TTS 1.5 is a high-fidelity local TTS foundation model with stronger multilingual synthesis, stable voice cloning, long-form control, and expressive pause handling.
MOSS TTS 1.5 supports 31 languages, including multilingual and code-switched speech workflows.
Its upgraded audio tokenizer enables native 48 kHz stereo output for detailed, studio-oriented synthesis.
The model improves voice-cloning stability, long-reference short-text cloning, punctuation-aware prosody, and inline pause control such as [pause 3.2s].
In OpenVox, MOSS TTS 1.5 is available on Mac and Windows and runs locally after the model is downloaded.
OpenVox does not provide celebrity voice models and does not permit cloning, impersonating, or commercially using any person's voice without proper rights or consent.
Open-source model: OpenMOSS / MOSS-TTS
View on Hugging Face