Skip to Content
APP • YONDA-AUDIO-PIPELINE

Pluggable Audio & Audio-Loom Engine

The audio engine automatically chooses the optimal voice pipeline based on current network bandwidth and content sensitivity:

Blake Carter|Version v3.0.0|CANONICAL
Content TierOptimal EngineFallback Engine (Offline)
Sacred / Indigenous LoreElevenLabs Custom Voice ModelHigh-Quality On-Device TTS
Historical & FolkloreElevenLabs Standard / StreamingOn-Device TTS (flutter_tts)
Commercial / Bakery / PubsDevice Native TTSOn-Device TTS

Audio Production Scripting

The AI output includes:

  1. Primary Spoken Vocal Track
  2. Ambience Track: Background loop at 15% volume (rain_on_windshield, 1920s_jazz, eerie_wind_loop)
  3. Sound FX Markers: Precise timestamp events triggering ambient audio effects.