Verified record · from the answer index
lucataco/step-audio-tts-3b
modeltested · static-verifiedscore 47/100signed passport ✓published 627d ago · verified 2026-10-241,100 uses
Step-Audio-TTS-3B represents the industry's first Text-to-Speech (TTS) model trained on a large-scale synthetic dataset utilizing the LLM-Chat paradigm
Declared tools (1)
lucataco/step-audio-tts-3b
model:replicate:lucataco/step-audio-tts-3b