Models
MOSS-TTS
OpenMOSS/MOSS-TTS
An open-source speech model family for long-form TTS, dialogue synthesis, voice design, and streaming speech.
Topics
Related projects
voxcpm41.3kAn open-source 2B tokenizer-free multilingual TTS model for voice design, controllable cloning, and studio-quality synthesis.
yovoice2.1kA local-first desktop studio for speech, voice cloning, singing, and music production, running text-to-speech and generative audio models entirely on the user's machine without cloud fees.
ComfyUI-VoxCPM521A ComfyUI custom node that integrates the VoxCPM tokenizer-free TTS system, enabling expressive speech synthesis, voice design, zero-shot voice cloning and LoRA fine-tuning inside ComfyUI workflows.
MOSS-Transcribe-Diarize2.3kAn open 0.9B end-to-end audio model for long-form transcription in 50+ languages, with speaker diarization, timestamps, and acoustic event awareness. The repo ships inference code, serving recipes, a subtitle web app, and fine-tuning guidance.
Confucius4-TTS852Confucius4-TTS is an open multilingual, cross-lingual zero-shot text-to-speech model that clones a speaker's voice across 14 languages while preserving emotion and identity.
anything-llm68.1kAn all-in-one self-hosted AI platform to chat with docs, run agents and manage models and users privately.