The recipe
Runtime
NaN:NaN
Scenes
4
Aspect ratio
9:16
Credit cost
156 / 308 cr
Video model
Vidu Q3 Image to Video
Category
Podcast
Published
April 22, 2026
Cloned by
1 creators
Reference images
The 4 reference assets every scene below draws character, product or set continuity from.
Podcast Host
characterThe host of the podcast — confident, engaging, professional on-camera presence.
Podcast Guest
characterThe guest being interviewed — thoughtful, articulate, expressive.
Host View Studio
locationPodcast studio shot from the host's angle — professional lighting, microphone in frame, modern set design.
Guest View Studio
locationPodcast studio shot from the guest's angle — professional lighting, microphone in frame, matching set design.
Scene-by-scene breakdown
Every image prompt, video prompt and voiceover line used to build this video, in order. Copy any block and swap in your own subject.
- 1s
Host Intro
Image prompt
podcast_host sitting in the host_view_studio, speaking into the microphone, professional podcast lighting, medium shot, looking at the guest.
Video prompt
Medium shot, podcast_host gesturing while speaking, professional studio lighting, realistic podcast setting.
- 2s
Guest Response
Image prompt
podcast_guest sitting in the guest_view_studio, listening intently, professional podcast lighting, medium shot, looking at the host.
Video prompt
Medium shot, podcast_guest nodding and responding, professional studio lighting, realistic podcast setting.
- 3s
Host Follow-up
Image prompt
podcast_host sitting in the host_view_studio, smiling and asking a follow up question, professional podcast lighting.
Video prompt
Medium shot, podcast_host smiling and talking into the microphone.
- 4s
Guest Conclusion
Image prompt
podcast_guest sitting in the guest_view_studio, smiling confidently while finishing their point.
Video prompt
Medium shot, podcast_guest smiling and leaning back slightly, finishing their point.
Frequently asked questions
How much does the "Podcast with me" workflow cost to generate?+
This exact workflow costs 156 credits in Versely at preview resolution, or 308 credits for the full-resolution render — spread across its 4 scenes.
What AI video model does "Podcast with me" use?+
Every scene is animated with Vidu Q3 Image to Video, rendering each of the 4 scenes before they're stitched into the final NaN:NaN cut.
How long is the finished video?+
The full edit runs NaN:NaN across 4 scenes in 9:16, sized for TikTok, Instagram Reels and YouTube Shorts.
Can I edit the prompts, voiceover or reference images?+
Yes — every scene's image prompt, video prompt and voiceover line is fully editable in Versely, and you can swap out any of the reference images (like the Podcast Host, Podcast Guest, Host View Studio, Guest View Studio) for your own.
How many creators have cloned this workflow?+
1 creator has cloned "Podcast with me" inside Versely as a starting point for their own version.
What category is "Podcast with me" filed under?+
It's filed under Podcast on Versely, tagged podcast, interview, ai, conversation, talk-show.
Related workflows
Build it with
Build “Podcast with me” inside Versely
The all-in-one AI studio for creators. 60+ models for video, image, voice, music and lipsync in a single app.