Audio arrives as a full citizen on the canvas. FAUNA chat is roughly 3× faster to first token, and more.

📦 New

• Audio Nodes — a dedicated audio node with waveform playback, voice selector, ElevenLabs text-to-speech and speech-to-text, Gemini audio inputs, and automatic routing that picks the right model for music, speech, or sound effects. Perfect for narration, sound design, and podcast-style workflows.

• Layer Editor Rewrite — new stencil masking, shapes, text rotation, multi-select resize/rotate, drag-to-adjust numeric inputs (hold and drag any number field), and a proper empty state.

• Technique Picker in Add-Node Menu — search techniques with hover-preview thumbnails right from the canvas.

• Cmd + \ — Keyboard shortcut to toggle all canvas toolbars to maximize your workspace.

• Batch grouping in generation history — variants from the same batch are grouped and highlighted together in the carousel.

  
  

  🧠 Improved

• FAUNA chat — roughly 3× faster to first token

• Long FAUNA sessions — now compact automatically, so conversations stay responsive over time

•