Qwen3 ASR Demo
👀
263
Convert uploaded audio to text with language detection
SPEECH TO TEXT
-
-
Whisper
📉2.81kTranscribe audio or YouTube video into text
-
openai/whisper-large-v3
Automatic Speech Recognition • 2B • Updated • 5.86M • • 6.01k -
Qwen3 Omni Captioner Demo
🐠66Generate a caption for any uploaded or recorded audio
-
Qwen/Qwen3-Omni-30B-A3B-Captioner
Any-to-Any • 32B • Updated • 21.1k • 236 -
nvidia/parakeet-tdt-0.6b-v3
Automatic Speech Recognition • 0.6B • Updated • 184k • • 1.02k -
LiquidAI/LFM2-Audio-1.5B
Audio-to-Audio • 1B • Updated • 249 • 358 -
Whisper Web
🎤1.29kTranscribe audio files to text instantly
-
microsoft/VibeVoice-ASR
Automatic Speech Recognition • 9B • Updated • 694k • 1.25k -
Open ASR Leaderboard
🏆1.42kExplore speech model benchmarks across languages and datasets
-
CohereLabs/cohere-transcribe-03-2026
Automatic Speech Recognition • 2B • Updated • 1.06M • • 1.07k -
alexandradiaconu/whisper-small-financiar-mix14
0.2B • Updated • 1 -
Qwen/Qwen3-ASR-1.7B
Automatic Speech Recognition • 2B • Updated • 1.97M • • 965 -
mradermacher/gemma-3n-E4B-it-absolute-heresy-MPOA-GGUF
Automatic Speech Recognition • 7B • Updated • 579 • 2