Launchpad
Choose a mode, then launch the workflow from one place.
Capability Launchpad
Pick a mode from the capability map, launch the workflow, and move through the stack in one shell.
Voice Clone (Simple Flow)
3 steps only: upload reference, type script, click generate.
Step 1: Upload Reference Audio
If no file is uploaded, system will run in auto mode.
Step 2: Final Script
Paste the final text you want to generate.
Optional: Reference Transcript
Optional, but helps stability for clone mode.
Advanced Preview (optional)
Use this only when you want quick A/B checks before final generation.
Advanced Profiles (optional)
Design Workbench
Build profile-driven voices with prompt presets, preview, and final render controls.
Voice Attributes
Prompt-level control of persona and speaking style
Final Generation Script
Main text for final output render
Preview Studio
Short test render before long final output
Final Output
Main designed voice output
Download WAVFinal output will appear here after generation.
Transcription Studio
Upload audio, transcribe with timestamps, edit segments, and export subtitle assets.
Available languages: coming from backend API
Status
This mode is wired as Ready in UI. Connect ASR backend endpoint when enabled in production policy.
OmniDrive
Unified storage for batch manifests, transcriptions, profiles, and generated assets.
Folders
Assets
Settings Control Center
Central view for models, engines, logs, and credential readiness.
Models Runtime
Loading...
Logs & Runtime
Loading...
Security Status
Loading...
Current Job Access
No job yet
System Version Endpoint
Source: /api/system/version
Loading...
OpenAI Models Endpoint
Source: /v1/models
Loading...
Non-verbal Control
Validate tags before generation: /api/nonverbal/tags and /api/nonverbal/validate
Validation result will appear here.
Pronunciation Lexicon
Tenant dictionary manager: /api/pronunciation/lexicons
Save response will appear here.
Lexicon list will appear here.
Loading Turnstile...