Qwen/Qwen2.5-Omni-3B
Any-to-Any • Updated
• 231k • 328
Speech to Speech
-
-
Open ASR Leaderboard
🏆1.22kExplore ASR model performance across languages and datasets
-
fishaudio/s1-mini
Text-to-Speech • Updated • 5.33k • 593 -
fluxions/vui
Text-to-Speech • Updated • 765 • 147 -
OpenMOSS-Team/MOSS-TTSD-v0
Text-to-Speech • 2B • Updated • 27 -
nvidia/audio-flamingo-3
Audio-Text-to-Text • Updated • 278 • 142 -
bosonai/higgs-audio-v2-generation-3B-base
Text-to-Speech • Updated • 199k • 658 -
Vyvo/VyvoTTS-v0-Qwen3-0.6B
Text-to-Speech • 0.8B • Updated • 110 • 25 -
nvidia/canary-1b-v2
Automatic Speech Recognition • Updated • 287k • 361 -
nvidia/diar_streaming_sortformer_4spk-v2
Automatic Speech Recognition • Updated • 31.3k • 102 -
microsoft/VibeVoice-1.5B
Text-to-Speech • 3B • Updated • 141k • 2.22k -
stepfun-ai/Step-Audio-2-mini
Any-to-Any • Updated • 1.86k • 250 -
FireRedTeam/FireRedTTS2
Updated • 65 -
ThomasG/faster-whisper-large-v3-turbo-int8-fp16
Automatic Speech Recognition • Updated • 13