Speech-to-Text to Image Generator & Sound Detector

API Credentials

ElevenLabs API Key:

fal.ai API Key:

Speech & Presentation Controls

Status: Idle

Sound Detector (Bang Trigger)

Detects sudden loud noises (bangs/slaps/claps). Triggering a hit is equivalent to pressing the Enter key (advances images during Presentation Mode).

Sensitivity (1 - 100): 60

Current Peak:

Sound Event Log

Live Delta (Partial Transcript)