Qwen/Qwen2.5-Omni-3B
Any-to-Any • 6B • Updated • 1.7M • 336
Speech to Speech
-
-
Open ASR Leaderboard
🏆1.39kExplore and compare speech‑recognition model benchmarks
-
fishaudio/s1-mini
Text-to-Speech • Updated • 3.04k • 661 -
fluxions/vui
Text-to-Speech • Updated • 152 • 150 -
OpenMOSS-Team/MOSS-TTSD-v0
Text-to-Speech • 2B • Updated • 11 • 28 -
nvidia/audio-flamingo-3
Audio-Text-to-Text • Updated • 426 • 151 -
bosonai/higgs-tts-2-3b-base
Text-to-Speech • 6B • Updated • 181k • 684 -
Vyvo/VyvoTTS-v0-Qwen3-0.6B
Text-to-Speech • 0.8B • Updated • 14 • 25 -
nvidia/canary-1b-v2
Automatic Speech Recognition • Updated • 106k • 397 -
nvidia/diar_streaming_sortformer_4spk-v2
Automatic Speech Recognition • Updated • 29.2k • 125 -
microsoft/VibeVoice-1.5B
Text-to-Speech • 3B • Updated • 237k • 2.41k -
stepfun-ai/Step-Audio-2-mini
Any-to-Any • 8B • Updated • 12.4k • 259 -
FireRedTeam/FireRedTTS2
Updated • 67 -
ThomasG/faster-whisper-large-v3-turbo-int8-fp16
Automatic Speech Recognition • Updated • 15 -
SkunkWorkLabs/varuna-stt
Automatic Speech Recognition • Updated • 13 -
OpenMOSS-Team/MOSS-TTS-Local-Transformer-v1.5
Text-to-Speech • 5B • Updated • 11.4k • 54