TTS Models Text-to-speech and voice generation models to try. Supertone/supertonic-3 Text-to-Speech • Updated May 18 • 83.2k • 1.03k fishaudio/s2-pro Text-to-Speech • 5B • Updated Mar 11 • 47.5k • 1.49k k2-fsa/OmniVoice Text-to-Speech • 0.6B • Updated Jul 3 • 2.86M • 1.64k IndexTeam/Index-TTS Text-to-Speech • Updated Apr 27, 2025 • 156 • 155
Local Models for OpenClaw antirez/deepseek-v4-gguf Text Generation • 284B • Updated Aug 31 • 1.1M • 495 nvidia/Qwen3.6-27B-NVFP4 Text Generation • 18B • Updated Jun 30 • 572k • 447 nvidia/Gemma-4-31B-IT-NVFP4 Text Generation • 21B • Updated Jul 13 • 1.07M • • 588 nvidia/Qwen3.6-35B-A3B-NVFP4 Text Generation • 19B • Updated Aug 29 • 3.82M • 673
TTS Models Text-to-speech and voice generation models to try. Supertone/supertonic-3 Text-to-Speech • Updated May 18 • 83.2k • 1.03k fishaudio/s2-pro Text-to-Speech • 5B • Updated Mar 11 • 47.5k • 1.49k k2-fsa/OmniVoice Text-to-Speech • 0.6B • Updated Jul 3 • 2.86M • 1.64k IndexTeam/Index-TTS Text-to-Speech • Updated Apr 27, 2025 • 156 • 155
Local Models for OpenClaw antirez/deepseek-v4-gguf Text Generation • 284B • Updated Aug 31 • 1.1M • 495 nvidia/Qwen3.6-27B-NVFP4 Text Generation • 18B • Updated Jun 30 • 572k • 447 nvidia/Gemma-4-31B-IT-NVFP4 Text Generation • 21B • Updated Jul 13 • 1.07M • • 588 nvidia/Qwen3.6-35B-A3B-NVFP4 Text Generation • 19B • Updated Aug 29 • 3.82M • 673