Qwen/Qwen2.5-Omni-3B
Any-to-Any • Updated • 810k • 334
Speech to Speech
-
-
Open ASR Leaderboard
🏆1.33kExplore and compare speech recognition model benchmarks
-
fishaudio/s1-mini
Text-to-Speech • Updated • 3.16k • 642 -
fluxions/vui
Text-to-Speech • Updated • 992 • 147 -
OpenMOSS-Team/MOSS-TTSD-v0
Text-to-Speech • 2B • Updated • 8 • 28 -
nvidia/audio-flamingo-3
Audio-Text-to-Text • Updated • 291 • 148 -
bosonai/higgs-audio-v2-generation-3B-base
Text-to-Speech • 6B • Updated • 91.2k • 670 -
Vyvo/VyvoTTS-v0-Qwen3-0.6B
Text-to-Speech • 0.8B • Updated • 16 • 25 -
nvidia/canary-1b-v2
Automatic Speech Recognition • Updated • 161k • 380 -
nvidia/diar_streaming_sortformer_4spk-v2
Automatic Speech Recognition • Updated • 24.6k • 116 -
microsoft/VibeVoice-1.5B
Text-to-Speech • 3B • Updated • 266k • 2.36k -
stepfun-ai/Step-Audio-2-mini
Any-to-Any • Updated • 3k • 254 -
FireRedTeam/FireRedTTS2
Updated • 66 -
ThomasG/faster-whisper-large-v3-turbo-int8-fp16
Automatic Speech Recognition • Updated • 17 -
SkunkWorkLabs/varuna-stt
Automatic Speech Recognition • Updated • 10