Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice
Text-to-Speech • 2B • Updated • 2.14M • 1.63k
Voz (TTS + STT)
Melhores modelos open-source de voz: sintese (TTS) e ASR (STT). · Curadoria Mangaba AI 🥭
-
-
openbmb/VoxCPM2
Text-to-Speech • 2B • Updated • 529k • 1.42k -
Supertone/supertonic-3
Text-to-Speech • Updated • 53.9k • 851 -
Qwen/Qwen3-ASR-1.7B
Automatic Speech Recognition • 2B • Updated • 1.62M • 898 -
nvidia/parakeet-tdt-0.6b-v3
Automatic Speech Recognition • 0.6B • Updated • 172k • • 941 -
CohereLabs/cohere-transcribe-03-2026
Automatic Speech Recognition • 2B • Updated • 736k • 1.01k -
hexgrad/Kokoro-82M
Text-to-Speech • Updated • 16.2M • • 6.38k -
k2-fsa/OmniVoice
Text-to-Speech • 0.6B • Updated • 1.26M • 1.07k -
fishaudio/s2-pro
Text-to-Speech • 5B • Updated • 369k • 1.05k