VoxTurn Open turn-taking models for voice agents: end-of-turn, barge-in and backchannel detection. voxturn (multilingual) + ShadowMe (speaker-aware). AustinXiao/voxturn Audio Classification • Updated 8 days ago • 464 • 8 AustinXiao/voxturn-personal-turn-detector Audio Classification • Updated 8 days ago • 111 Running on Zero MCP voxturn 🎙 Open turn detector - has the user finished talking?
VeriSpoof Beyond real or fake: one unified audio LLM for speech deepfake forensics. AustinXiao/VeriSpoof-Plus Audio-Text-to-Text • 3B • Updated 8 days ago • 106 • 2 AustinXiao/VeriSpoof-Base Audio-Text-to-Text • 3B • Updated 8 days ago • 232 • 4 AustinXiao/VeriSpoof-Bench Viewer • Updated 9 days ago • 356k • 716 Running on Zero Agents VeriSpoof 🔎 Beyond real or fake: one unified audio LLM for deepfakes
VoxTurn Open turn-taking models for voice agents: end-of-turn, barge-in and backchannel detection. voxturn (multilingual) + ShadowMe (speaker-aware). AustinXiao/voxturn Audio Classification • Updated 8 days ago • 464 • 8 AustinXiao/voxturn-personal-turn-detector Audio Classification • Updated 8 days ago • 111 Running on Zero MCP voxturn 🎙 Open turn detector - has the user finished talking?
VeriSpoof Beyond real or fake: one unified audio LLM for speech deepfake forensics. AustinXiao/VeriSpoof-Plus Audio-Text-to-Text • 3B • Updated 8 days ago • 106 • 2 AustinXiao/VeriSpoof-Base Audio-Text-to-Text • 3B • Updated 8 days ago • 232 • 4 AustinXiao/VeriSpoof-Bench Viewer • Updated 9 days ago • 356k • 716 Running on Zero Agents VeriSpoof 🔎 Beyond real or fake: one unified audio LLM for deepfakes