tts-1.6b-en_fr is a 1.6 billion parameter text-to-speech model developed by Kyutai as part of the Moshi project. It supports both English and French and can be run locally using the Moshi library with a simple web server interface. The model uses a Mimi audio codec for encoding and decoding and is accompanied by academic papers detailing its architecture and performance.
In the Voice, TTS & speech space, Tts 1.6b En Fr takes a focused approach. It focuses on generating high-quality, natural-sounding speech in English and French from text using an open model that runs locally. It is built as an open-source project for developers. The project is open source (Apache-2.0). Tts 1.6b En Fr is available on the web and the command line, and it can be self-hosted.
It is developed by Kyutai, and it first shipped in 2025. Development happens publicly on GitHub with 3k stars. Key capabilities include text-to-Speech, multilingual, and Moshi Integration. It exposes integrations via a public API.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do