Qwen3 ASR Demo
👀
264
Transcribe uploaded audio to text with language detection
SPEECH TO TEXT
-
-
Whisper
📉2.89kTranscribe audio files into written text
-
openai/whisper-large-v3
Automatic Speech Recognition • 2B • Updated • 3.64M • • 6.71k -
Qwen3 Omni Captioner Demo
🐠68Generate captions for your audio recordings
-
Qwen/Qwen3-Omni-30B-A3B-Captioner
Any-to-Any • 32B • Updated • 9.94k • 259 -
nvidia/parakeet-tdt-0.6b-v3
Automatic Speech Recognition • 0.6B • Updated • 586k • 1.23k -
LiquidAI/LFM2-Audio-1.5B
Audio-to-Audio • 1B • Updated • 383 • 365 -
Whisper Web
🎤1.3kTranscribe audio recordings into written text
-
microsoft/VibeVoice-ASR
Automatic Speech Recognition • 9B • Updated • 686k • 1.32k -
Open ASR Leaderboard
🏆1.51kCompare speech recognition models across datasets and languages
-
CohereLabs/cohere-transcribe-03-2026
Automatic Speech Recognition • 2B • Updated • 99.5k • • 1.21k -
alexandradiaconu/whisper-small-financiar-mix14
0.2B • Updated • 5 -
Qwen/Qwen3-ASR-1.7B
Automatic Speech Recognition • 2B • Updated • 1.42M • • 1.22k -
mradermacher/gemma-3n-E4B-it-absolute-heresy-MPOA-GGUF
Automatic Speech Recognition • 7B • Updated • 507 • 2