Output Engine v1 · Dual-Provider Audio Engine
Review your audio narration
Select a script section and generate spoken narration via OpenAI TTS and ElevenLabs TTS simultaneously. Both provider outputs are presented for comparison. Approve the narration set before downstream use.
Generate audio narration
Select a script section to narrate. Stage directions are stripped automatically. Both OpenAI TTS and ElevenLabs TTS will be called in parallel. This takes 10–30 seconds.
Stage directions in brackets are removed before sending to providers.
Selected section preview
Generating audio narration…
Calling OpenAI TTS and ElevenLabs TTS in parallel. This takes 10–30 seconds. Do not close the page.
Script section
Narration script sent to providers
Approve or reject this audio narration
Approve to clear this narration set for downstream use. Reject to regenerate with a different section or after revising your ProductTruth.
Describe what is wrong with this narration.
Audio narration approved.
Combine this narration with approved image assets to create a video composition.
Audio narration rejected.
Return to intake