All models
long-form

MOSS-TTS v1.5

Apache-2.0

Long-form multilingual narration with cloning and explicit pause controls.

Long-form multilingual narration with cloning and explicit pause controls. The model card lists 31 languages; shown language codes are a subset. This is the 8B delay model, not the Local Transformer or Nano variant.

Hear MOSS-TTS v1.5

Standardized samples are pending for this release. See the official sources below for the author’s demo.

MOSS-TTS v1.5 · Default · Same three scripts across the directory.

Best for: Long-form multilingual narration with cloning and explicit pause controls.

Before you choose: The model card lists 31 languages; shown language codes are a subset. This is the 8B delay model, not the Local Transformer or Nano variant.

No comparable hardware benchmark verified. Check the official setup for your device.

Details reviewed 2026-09-14. Hardware figures are estimates unless a benchmark is linked.

No samples yet

Every model in this directory is read against the same three scripts so voices can be compared honestly — MOSS-TTS v1.5’s samples just haven’t been generated yet.

Contribute samples on GitHub →

Run MOSS-TTS v1.5

git clone https://github.com/OpenMOSS/MOSS-TTS.git
cd MOSS-TTS
# Follow the v1.5 model-card quickstart.

MOSS-TTS v1.5 FAQ

Do I need a GPU to run MOSS-TTS v1.5?

We have not verified a hardware requirement for this release. Follow the official setup instructions.

Can MOSS-TTS v1.5 clone voices?

Yes — MOSS-TTS v1.5 supports voice cloning from reference audio.

What license is MOSS-TTS v1.5 released under?

MOSS-TTS v1.5 is released under the Apache-2.0 license. Always check the repository for the exact terms — some models license code and weights separately.

What languages does MOSS-TTS v1.5 support?

MOSS-TTS v1.5 supports English, Chinese, Japanese, Korean, German, French, Spanish, Italian, Portuguese, Russian, Arabic, Hindi.

Is there a hosted MOSS-TTS v1.5 API?

OpenSpeech Cloud is accepting production-access interest for MOSS-TTS v1.5, but this model is not hosted in the beta. Use the official repository for current deployment options.