Qwen/Qwen2.5-Omni-3B
Any-to-Any
•
6B
•
Updated
•
233k
•
328
Speech to Speech
-
-
Open ASR Leaderboard
🏆1.21kCompare and evaluate speech recognition model performance across multiple benchmarks
-
fishaudio/openaudio-s1-mini
Text-to-Speech • Updated • 4.86k • 565 -
fluxions/vui
Text-to-Speech • Updated • 403 • 146 -
OpenMOSS-Team/MOSS-TTSD-v0
Text-to-Speech • 2B • Updated • 2 • 27 -
nvidia/audio-flamingo-3
Audio-Text-to-Text • Updated • 762 • 140 -
bosonai/higgs-audio-v2-generation-3B-base
Text-to-Speech • 6B • Updated • 164k • 657 -
Vyvo/VyvoTTS-v0-Qwen3-0.6B
Text-to-Speech • 0.8B • Updated • 277 • 25 -
nvidia/canary-1b-v2
Automatic Speech Recognition • Updated • 236k • 349 -
nvidia/diar_streaming_sortformer_4spk-v2
Automatic Speech Recognition • Updated • 21.7k • 100 -
microsoft/VibeVoice-1.5B
Text-to-Speech • 3B • Updated • 329k • 2.21k -
stepfun-ai/Step-Audio-2-mini
Any-to-Any • Updated • 1.11k • 247 -
FireRedTeam/FireRedTTS2
Updated • 64