MOSS-TTS Nano

MOSS-TTS Nano TTS

A 100M-parameter MOSS-TTS variant — same delay-transformer family, ~80x smaller, tuned for free-tier latency.

MOSS-TTS Nano is OpenMOSS's compact 100-million-parameter sibling to the flagship MOSS-TTS, sharing the same delay-transformer architecture but roughly 80x smaller. It gives up the 8B model's peak quality in exchange for far lower per-request VRAM (~2GB) and fast ~2-second generation, which makes it well suited to free-tier and high-throughput deployments. It keeps broad multilingual reach across 11 languages and, unlike many lightweight models, still supports zero-shot voice cloning. The result is a budget-friendly option for high-volume or low-latency interactive use where speed and cost matter more than studio fidelity.

At a glance

Developer
OpenMOSS
License
Apache 2.0
Tier
free
Speed
fast
Voice cloning
Yes
Languages
English, Chinese, German, Spanish, French, Japanese, Italian, Korean, Russian, Arabic, Portuguese
Max characters
5000

MOSS-TTS Nano AI Voices

Arabic

Arabic
Па змаўчанні Neutral
Выкарыстоўваць

Chinese

Chinese
Па змаўчанні Neutral
Выкарыстоўваць

Default

English
Па змаўчанні Neutral
Выкарыстоўваць

French

French
Па змаўчанні Neutral
Выкарыстоўваць

German

German
Па змаўчанні Neutral
Выкарыстоўваць

Italian

Italian
Па змаўчанні Neutral
Выкарыстоўваць

Japanese

Japanese
Па змаўчанні Neutral
Выкарыстоўваць

Korean

Korean
Па змаўчанні Neutral
Выкарыстоўваць

Portuguese

Portuguese
Па змаўчанні Neutral
Выкарыстоўваць

Russian

Russian
Па змаўчанні Neutral
Выкарыстоўваць

Spanish

Spanish
Па змаўчанні Neutral
Выкарыстоўваць

Best for

Free-tier TTS, high-volume production, low-latency interactive use

MOSS-TTS Nano TTS — FAQ

Nano is the 100M version of the 8B MOSS-TTS — about 80x smaller and much faster (~2s, ~2GB VRAM). It trades the flagship's top quality for free-tier latency while keeping the same delay-transformer architecture.

Yes. Despite its small size, MOSS-TTS Nano supports voice cloning from a short reference clip (around 3 seconds).

Yes. It sits in the free tier and is Apache 2.0 licensed. It supports 11 languages, including English, Chinese, German, Spanish, French, Japanese, Italian, Korean, Russian, Arabic, and Portuguese.
← All voices