Lip-sync to the original
The front voice mouths the original verse into the single mic, in time with the recording.
Audio included
Hotel Lobby AI with the original song means the track is already inside the file you download. Plenty of tools export a mute clip and leave the music to TikTok; here Wan 3.0 films your pair on the orange set, the left face mouthing the Hotel Lobby recording and the right face reacting to it.
Your two faces
A single face per picture. Left leads, right backs up.
Set
Take and sound
Price: 6 credits. Done in roughly 5 to 15 min; if it fails, the credits come back. See prices
Yes. Hotel Lobby Video (hotel-lobby-video.app) keeps the original Hotel Lobby song by default. Upload two portraits and leave the setting on Hotel Lobby original with Wan 3.0: the left person lip-syncs the original recording at the mic, the right person reacts, and the downloaded MP4 already carries the audio, so nothing needs adding in TikTok. 12 seconds at 480p costs 6 credits, packs start at 10 credits for $9.99 with no subscription, and a take usually lands in about 5 to 15 minutes. The Seedance models are different: they write a new AI rap rather than keeping the song.
Last revised
Where the audio comes from
Wan 3.0, the default model in this studio, receives the Hotel Lobby recording as the audio to follow, cut to the same seconds as the choreography. In our tests the vocals in finished takes tracked the original closely (a correlation of 0.90 to 0.97 on the vocal passages), and the front voice lip-syncs to it while the sidekick moves on the beat, as in the COLORS session.
Across the trend you will find three approaches to sound. One exports a silent video and tells you to attach the Hotel Lobby sound in TikTok. One generates a new AI song, so your clip sounds like a different record. One keeps the original recording in the file. This page is the third approach.
The audio always starts at the top of the performance: a 5-second take gets the first 5 seconds, a 15-second take the first 15. You cannot pick a later section of the original. For a different section or a different track, upload it as your own song.
Models that generate their own audio cannot just reuse a famous recording. Seedance, our other model family, refuses requests that include the original track: 6 of our paid tests were blocked over audio copyright. Tools built on that kind of model ship the clip mute or write a fresh AI rap. Wan 3.0 follows whatever track it is handed, which is why it can keep the song.
No. The audio being in your MP4 is not a licence. Hotel Lobby Video has no connection to the artists or their label and cannot grant rights to the recording. For a public TikTok or Reels post, the platform’s own Hotel Lobby sound is the licensed copy: attach it while posting and lower the clip’s audio so the two do not clash.
Session plan
A portrait of each person, or one shot of both. The left face performs the original verse; the right face plays backup.
It already reads Hotel Lobby original on Wan 3.0: the routine plus the original track. Choose a length (5, 8, 10, 12 or 15 seconds) and a shape; 9:16 for TikTok and Reels.
12 seconds at 480p is 6 credits. The MP4 you save plays the original song.
In the file
The front voice mouths the original verse into the single mic, in time with the recording.
You do not need to search for a sound in TikTok or line anything up in CapCut. Press play and the song is there.
Upload a dance clip of your own under Moves and keep the Hotel Lobby track: your pair performs your steps over the original. How it works is in the reference video guide.
480p, 720p or 1080p. 480p is preselected; each step up in resolution costs more credits.
| Sound setting | Model | Audio in the download |
|---|---|---|
| Hotel Lobby original (default) | Wan 3.0 | The original Hotel Lobby recording, from the top of the performance |
| Your song | Wan 3.0 | 2 to 15 seconds of your uploaded audio |
| AI rap | A Seedance model | A newly written verse and beat, not the original |
Not sure which to pick? If the point is to look like the trend, keep the original. If the point is a joke only your friends get, write it with AI rap or record it yourself. Prices are on the pricing page.
Our own takes
Two sample renders, with model, length and source shown under each. They demonstrate the workflow, not a promise about how often a take succeeds.
Wan 3.0 · 480p · 10 s · 16:9
Wan 3.0 · 720p · 12 s · 16:9
Around the web
These clips show the format. Other people made them with other tools, and each one is credited and linked to its post. They are not output from Hotel Lobby Video.
It already has it, as long as you keep the default Hotel Lobby original setting on Wan 3.0. Press play on the MP4 and the original song is there.
You do not have to. If you do add TikTok’s Hotel Lobby sound for licensing, turn the clip’s own audio down so you do not hear it twice.
Not with the original track: it always plays from the start of the performance for as long as the take runs. For another section, upload that section as your own song.
No. Sound has no effect on the price: 3, 4, 5, 6 or 7 credits for 5, 8, 10, 12 or 15 seconds at 480p.
Very. The original recording is passed to the model as the track to follow, and in our tests the vocals in finished takes matched it at a correlation of 0.90 to 0.97. No new lyrics get written.
No. AI rap on a Seedance model writes a new verse and beat. It follows the rhythm of the Hotel Lobby track, not its words, melody or voices.
No. Each take is paid in credits at the moment you create it. The smallest pack is 10 credits for $9.99, and a failed take refunds itself.
Label it as AI-made and cast only people who agreed. We do not license the song to you; for a public post, TikTok’s own Hotel Lobby sound is the licensed way to use it.
Audio included
Two portraits, the default sound, and an MP4 that plays the song the moment you open it.