OpenMOSS · Text-to-Speech
MOSS-TTS-Nano
0.1B-parameter open-source TTS model that generates 48kHz stereo audio in 20 languages with voice cloning, designed for CPU-only inference without GPUs. Pure autoregressive architecture with streaming generation and ~2x efficiency via ONNX CPU backend.
Open the source ↗Similar Audio & Speech releases
- Audio8-TTS-Realistic 0.6B
Audio8 (edge0-ai) · Compact multilingual TTS · Week 45, 2026
- Paradee-8M-v1.2
Sahil Mahendrakar · Tiny multi-voice TTS · Week 45, 2026
- Ming-3.0-tts
Inclusion AI (Ant Group) · Open TTS · Week 44, 2026
- KittenTTS 2
KittenML (Stellon Labs) · Voice Cloning TTS · Week 43, 2026
- Fish Audio Drama 3
Fish Audio · Directable TTS · Week 43, 2026
- VoiceStudio v0.5.6
debpalash · Local Voice Studio · Week 42, 2026
More from OpenMOSS
- MOSS-Image
OpenMOSS · Open Text-to-Image · Week 43, 2026
- MOSS-TTS
OpenMOSS · Text-to-Speech · Week 7, 2026
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.