MOSS-TTS-v1.5

Released
2026-05-26
Last refreshed
2026-06-29
Status
Researched 140d ago
Open sourceCommercial use: permittedAudio

MOSS-TTS-v1.5 is a released general LLM work model with open-source; evaluate it while provider pricing coverage matures.

MOSI AI releases · 9 in the last 12 months · this family litChangelog →
Specifications
Family
MOSS-TTS
Released
2026-05-26
Parameters
8B
Architecture
Audio / Speech
Specialization
text-to-speech
Openness
Open source
License
Apache 2.0OSI-approvedPermitted
Weights
Available
Code
Unknown
Training
Pretrained
Created by
MOSI AI

OpenMOSS speech, audio, and video foundation-model research.

Shanghai, China
Website
Pricing

No tracked provider pricing is available yet.

Links
Website HuggingFace

About

MOSS-TTS-v1.5 is an open-weight multilingual text-to-speech model from MOSI AI and the OpenMOSS team. The 8B-parameter MossTTSDelay model supports zero-shot voice cloning, long-form speech generation, explicit pause control with [pause X.Ys] markers, and language-tagged multilingual synthesis across 31 languages. Version 1.5 improves on MOSS-TTS v1.0 with stronger multilingual synthesis, more stable voice cloning, better long-reference short-text handling, and punctuation-driven prosody. The model weights are available on Hugging Face under Apache 2.0; no hosted token-priced API route is confirmed.

Providers

No active provider routes are tracked for this model yet.

Capabilities

Audio

Benchmark peer barsfor Coding

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.

API versions

MOSS-TTS-v1.5