Apache-2.0 model family: long-form TTS, MOSS-TTSD multi-speaker dialogue (up to ~60 minutes), voice design from text, streaming TTS, and sound-effect generation
MOSS-TTS Family is listed under AI Voice & Speech, in the Content & Media Generation category on Flocci AI Tools. Apache-2.0 model family: long-form TTS, MOSS-TTSD multi-speaker dialogue (up to ~60 minutes), voice design from text, streaming TTS, and sound-effect generation. It is free, with no paid plan attached, and it lives at github.com.
MOSS-TTS Family is listed as fully free — there is no paid tier attached to it in the catalog. That makes it one of the 397 entries on Flocci AI Tools with no upgrade path built in.
MOSS-TTS Family needs to be installed or self-hosted — it doesn't run in a browser tab. It is available on self-hosting and an API.
MOSS-TTS Family does 3 things the catalog singles out: Apache-2.0 model family: long-form tts, moss-ttsd multi-speaker dialogue (up to ~60 minutes), voice design from text, streaming tts, and sound-effect generation; 31 languages with code-switching; nano variant (0.1b) runs on cpu; from the shanghai openmoss lab.
Copilot Audio Expressions is the closest free alternative: it sits in the same AI Voice & Speech sub-category and is free. Kokoro Web, Zonos and Chatterbox (Resemble AI) also start free. The full list is on the alternatives page.
See the full list →