Hotel Lobby AI turns two photos into a duo rap music video with an original AI track and lip-synced vocals — up to 15 seconds, from $1.20 a video — and your first 5-second video is free when you sign up.
Track 09 · Heritage stage
Velvet Lounge Cypher Hotel Lobby AI video
Deep velvet, one vintage mic, an intimate exchange. Upload two photos, see them on this stage instantly for free, and render a video with an original beat and lip-synced rap — from $1.20.
What this stage looks like
A dark velvet lounge in magenta haze, with the two of you sharing a vintage ribbon microphone in a close two-shot. A subtle push-in and an intimate call-and-response make this the moodiest, most cinematic people stage.
Scene brief sent to the model
This is the exact scene description every Velvet Lounge Cypher render uses. You do not write a prompt — your photos set the faces and the first frame, and this brief sets the scene and movement.
Two performers share a vintage ribbon microphone in a dark velvet lounge, magenta haze, close two-shot, intimate call-and-response rap, subtle push-in.
Best for
- Couples making a moody, intimate clip
- Valentine’s Day or anniversary videos
- Duos who like a late-night, jazz-club atmosphere
Photos that work on this stage
- Close-up portraits suit the tight two-shot framing.
- Darker clothing works with the velvet and magenta haze.
- One clear, front-facing, evenly lit photo per person — no sunglasses or heavy filters.
Velvet Lounge Cypher price per video
| Tier | 5 s | 10 s | 15 s |
|---|---|---|---|
| Draft · 480p | $1.20 | $2.40 | $3.59 |
| Standard · 720p | $3.00 | $5.99 | $8.98 |
| Pro · 1080p | $7.99 | $15.97 | $23.96 |
Same price on every stage. Sound included at every tier. All packs and plans
FAQ
- Why is Velvet Lounge Cypher framed so closely?
- The brief asks for a close two-shot around a shared ribbon microphone, so faces fill more of the frame than on the open studio stages. Clear close-up photos give the best likeness here.
- How much does a Velvet Lounge Cypher video cost?
- From $1.20 for a 5-second Draft video with sound, up to $23.96 for 15 seconds at 1080p. New accounts get 60 free credits — one 5-second Draft video.
- Can I make a vertical Velvet Lounge Cypher video for TikTok?
- Yes. Velvet Lounge Cypher renders in 9:16 for TikTok, Reels and Shorts or 16:9 for YouTube, at 5, 10, 15 seconds.
Hotel Lobby AI at a glance
By the Hotel Lobby AI team · Updated
- What it is
- Hotel Lobby AI is an AI video generator. It is not a hotel booking, concierge or interior-design service, and it is not affiliated with Quavo, Takeoff, Migos or COLORS. It turns two photos into a two-person rap music video in the style of the "Hotel Lobby" trend.
- Input
- Two photos (JPG, PNG or WebP), one per performer, or one photo with both faces. People or pets. 14 stages: people, heritage and animal sets.
- Output
- MP4, 16:9 or 9:16, 5, 10 or 15 seconds, 480p, 720p or 1080p.
- Sound
- Every render has an original AI trap beat with lip-synced rap vocals. Each finished file is checked for an audio track; a silent render is refunded. The original "Hotel Lobby" recording is not included.
- Price per video
- Draft 480p $1.20–$3.59; Standard 720p $3.00–$8.98; Pro 1080p $7.99–$23.96 (Starter pack rate, $2.00 per 100 credits; down to $1.54 per 100 on bigger packs and plans).
- Credit packs and plans
- Starter 300 credits $5.99, Creator 900 credits $14.99, Studio 2600 credits $39.99 — pack credits never expire. Monthly plans: Lite $9.99, Basic $19.99, Pro $39.99.
- Free
- Stage preview in the browser with no account. 60 credits after email verification, one per person — one 5-second Draft video with sound. No card.
- Render time
- About five minutes for a typical render. The live queue and the median wait over the last 24 hours are shown before you generate. You can close the page while it renders.
- Refunds
- Credits for failed, moderation-blocked or silent renders are returned automatically.
- Your photos
- Photos are composited into one stage frame in your browser; that frame is kept until you delete the video or your account. Use only photos of people who agreed to appear — no celebrities or public figures, and minors only with a parent or guardian’s consent.
- Model
- fal.ai and APIMart (ByteDance Seedance 2.0 video models)