n8n Workflow: Create Talking-Head UGC Videos with Omni 1.1 Flash

Generate photorealistic talking-head UGC videos in n8n using Omni 1.1 Flash

This n8n workflow collects a presenter description and script via an n8n form, then uses the useapi.net Google Flow Images API (Nano Banana Pro) and the useapi.net Google Flow Videos API (Omni 1.1 Flash) to produce a downloadable talking-head MP4—automatically.

What this workflow does

• 1) Accepts input from an n8n form: the presenter description, short script, selected voice, and video orientation are submitted to the workflow.
• 2) Creates a photorealistic presenter portrait: the workflow calls useapi.net Google Flow Images API using Nano Banana Pro to generate an image reference.
• 3) Starts talking-head video generation: it launches an asynchronous job in useapi.net Google Flow Videos API with Omni 1.1 Flash, using the generated portrait and the selected voice.
• 4) Waits and checks job status: it waits 20 seconds, then polls the useapi.net Jobs API until the job completes or fails.
• 5) Downloads and outputs the final video: when ready, it downloads the completed video from the signed video URL and outputs it as an MP4 binary file (or stops with an error if the job fails).

Use cases

• Creating UGC-style product explainer videos from a script and voice, on-demand.
• Generating consistent presenter avatars for SaaS onboarding, updates, or announcements.
• Automating a content production pipeline where teams submit scripts and receive MP4 videos without manual rendering.

Technical details

• Integrations: useapi.net Google Flow Images API (Nano Banana Pro) and useapi.net Google Flow Videos API (Omni 1.1 Flash), plus useapi.net Jobs API.
• Prerequisites: Omni 1.1 Flash requires a paid Google AI plan (Plus, Pro, or Ultra) and uses Flow credits.
• Auth: add an n8n HTTP Header Auth credential for Authorization: Bearer <token> and select it on all HTTP Request steps.
• n8n nodes used: set, code, wait, switch, sticky note, form trigger.