MOSS TTSD is a web application that enables users to upload reference audio clips for up to five speakers and generate realistic multi-speaker conversations from text prompts. It is ideal for audio producers and content creators needing custom voice synthesis.
In the Voice cloning & synthesis space, MOSS TTSD takes a focused approach. It focuses on creating realistic multi-speaker audio conversations by cloning voices from reference audio and generating speech from text. MOSS TTSD is a consumer product aimed at audio producers. It is available for free. It runs on the web, and it can be self-hosted.
OpenMOSS-Team builds and maintains MOSS TTSD, and it first shipped in 2024. Among its 5 catalogued features are voice cloning, multi-speaker support, and reference audio upload.
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