🔊 Step-Audio-R1

Advanced Audio-Language Model with Reasoning

Comprehensive audio understanding: Speech, Sound, Music & Lyrics

1 56000
0 2
0 1

Display reasoning steps

📝 Your Input

📊 Audio limit: 10MB total available

Usage:

  • Type text, upload audio, or both
  • Audio > 25s auto-splits
  • Toggle thinking process display

Tips:

  • Thinking shown in blue gradient block
  • History auto-cleaned for API
  • Adjust params in Configuration