stepfun-ai/Step-Audio-R1
Audio-Text-to-Text • 33B • Updated • 17 • 146
Audio Multimodal Models
Open source models with audio understanding. Tracking mostly vendor releases in the audio and text to text subclassification of multimodal.
-
-
Qwen/Qwen2-Audio-7B
Audio-Text-to-Text • 8B • Updated • 21.9k • 181 -
Qwen/Qwen2-Audio-7B-Instruct
Audio-Text-to-Text • 8B • Updated • 200k • 571 -
FreedomIntelligence/Soundwave
Audio-Text-to-Text • 9B • Updated • 115 • 15 -
fixie-ai/ultravox-v0_7-glm-4_6
Audio-Text-to-Text • 0.7B • Updated • 230 • 41 -
fixie-ai/ultravox-v0_5-llama-3_2-1b
Audio-Text-to-Text • 0.7B • Updated • 76.4k • 96 -
AudioBench Leaderboard
🥇22View AudioBench leaderboard and compare model scores
-
Qwen/Qwen3-Omni-30B-A3B-Instruct
Any-to-Any • 35B • Updated • 725k • 1.04k -
mistralai/Voxtral-Mini-3B-2507
5B • Updated • 155k • 693 -
moonshotai/Kimi-Audio-7B-Instruct
Text-to-Speech • 10B • Updated • 12.7k • 421 -
microsoft/Phi-4-multimodal-instruct
Automatic Speech Recognition • 6B • Updated • 140k • 1.62k -
google/gemma-3n-E4B-it
Image-Text-to-Text • 8B • Updated • 12.2k • • 932 -
Qwen/Qwen-Audio
Text Generation • 8B • Updated • 1.15k • 163 -
google/gemma-3n-E2B
Image-Text-to-Text • 5B • Updated • 856 • 100 -
Qwen/Qwen-Audio-Chat
Text Generation • 8B • Updated • 1.28k • 103 -
nvidia/audio-flamingo-2
Audio-Text-to-Text • Updated • 49 -
nvidia/AudioSkills
Preview • Updated • 1.58k • 109 -
nvidia/audio-flamingo-3-hf
Audio-Text-to-Text • 8B • Updated • 45.4k • 201 -
nvidia/audio-flamingo-3
Audio-Text-to-Text • Updated • 511 • 162 -
NexaAI/OmniAudio-2.6B
Audio-Text-to-Text • 0.6B • Updated • 423 • 288 -
stepfun-ai/Step-Audio-Chat
Audio-Text-to-Text • 132B • Updated • 466 • 461
