Creating a UGC-style talking video with Pose AI takes three steps: get a photo, pick a talking-head template or HeyGen, and clone a voice with ElevenLabs. No camera, no filming, no separate editing tool.
This guide walks through the workflow start to finish.
- 3 steps: upload or generate a photo, select a UGC Template or HeyGen, clone your voice, then render.
- Everything runs inside Pose's Video Studio — photo generation, talking-head rendering, and voice cloning are not separate tools.
- 400 credits every week, from $4.99 the first week, then $14.99/week.
Step 1: Get your photo
Upload one clear selfie, or generate a photo first with Nano Banana 2 in Pose's Image Studio. Either way, Pose reads your identity from that single photo at generation time — there's no training step and no need to upload a batch of photos.
Step 2: Choose a UGC Template or HeyGen
UGC Templates give you a pre-built ad-style delivery format — product review, testimonial, or unboxing framing. HeyGen gives you a straight talking-head presenter format. Both are identity-locked to your uploaded photo.
Step 3: Clone your voice and render
Provide a short voice sample and Pose clones it natively through ElevenLabs — a speaking voice, not singing, and only for a voice you have the rights to use. Write or paste your script, and Pose renders the finished video with lip-synced audio.