Jump to main content

Your audio, their booth

Hotel Lobby AI With Your Own Song or Voice Note

Yes, you can swap the Hotel Lobby track for your own audio. Upload two photos plus 2 to 15 seconds of a song, a voice memo or a recorded birthday message, and the rapper in the orange booth lip-syncs your file while the partner hypes. Your audio adds nothing to the price.

  • 2 to 15 seconds of audio
  • Slide to the part you want
  • No extra charge for sound
  • Combine with your own moves
1

Your duo, one photo each

A single person per photo. Left raps, right hypes.

2

Stage

3

Video and audio

Cost: 6 credits. Takes roughly 5 to 15 minutes. If it fails, the credits come back. See prices

Quick answer

Hotel Lobby Video (hotel-lobby-video.com) lets you make the Hotel Lobby AI video with your own song. Choose Your song under Soundtrack & moves (already selected on this page), upload an MP3, WAV, M4A, AAC or OGG file and slide to the part you want; the lead lip-syncs that part on Wan 3.0. A 12-second clip at 480p is 6 credits, exactly the same as with the default track.

Last updated

Under the hood

How does a Hotel Lobby AI video follow my song?

Three inputs shape every Hotel Lobby AI clip. The two photos decide who stands in the booth. A reference routine decides the set, the framing and the choreography. A reference track decides what the lead mouths along to, and unless you change it, that track is the Hotel Lobby one.

Uploading your own audio swaps out only that last input. The booth, the camera and the partner’s moves stay as they are, and the lead now raps or sings your words into the hanging mic. Your browser trims the file to the length of the video (15 seconds at most), starting wherever you set the slider.

Pair it with your own reference clip if you like: the clip supplies the movement and your audio supplies the lip-sync. Whatever you upload, make sure you have the right to use it.

Which part of my track should I pick?

Start on a word, not on silence or a long intro, and pick a stretch where the vocal is loud and clear. A hook or a punchline usually lands best in 10 to 12 seconds. Spoken voice notes work as well as rap.

Upload to download

Making a Hotel Lobby video with your own song

  1. 01

    Add the two performers

    One clear photo each. The left photo is the lead who will mouth your audio; the right photo is the partner who reacts.

  2. 02

    Drop in your file

    Your song is already chosen under Soundtrack & moves, so just upload. If the recording is longer than the video, drag the slider to the section you want.

  3. 03

    Create and save

    6 credits buys a standard 12-second clip whichever sound you choose. Watch it, save the MP4, and know that a failed render refunds itself.

What to upload

Audio people send to the booth

01

A recorded birthday shout-out

Rap “happy birthday” into your phone for ten seconds, then put yourself and the birthday person in the booth to perform it.

02

A teaser for your track

Releasing music? Use the hook as the audio and two members of the band as the photos, and the teaser rides the trend.

03

The group-chat voice memo

That one voice note everybody quotes, delivered like a COLORS set. Short, clearly spoken clips sync best.

04

Bars you wrote yourself

Write a verse about your friend, record it over any beat, and let the lead deliver it in the booth.

What happens to your audio file

  1. You choose a file. MP3 is sent as it is; WAV, M4A, AAC and OGG are converted in the browser before upload.
  2. You set the start point. The browser keeps exactly the video length (5 to 15 seconds) from there and discards the rest.
  3. The trimmed audio takes the place of the Hotel Lobby track. Booth, camera, moves and price all stay the same.
  4. Wan 3.0 renders the lead lip-syncing your audio at the hanging mic, with the partner hyping and your audio as the soundtrack. No artist’s voice is cloned, so check the result before you post.

Can and cannot: your own song

It canIt cannot
Have the lead perform your song, rap or voice memoHave both people sing your upload (use AI rap with Both rap instead)
Use up to 15 seconds, the length of a typical TikTok or Reels clipTurn a whole song into a full music video
Follow your recording’s words and timingClone a famous voice, or promise a perfect copy of your file
Run on Wan 3.0, in the Hotel Lobby booth or over your own clipClean up noisy audio; clear vocals sync best

Prefer a verse written for you? The AI rap video generator composes an original rap on your topic using a Seedance model.

Made elsewhere

How Other Creators Did the Hotel Lobby Trend

These clips come from other creators and other tools. They show the format, not what Hotel Lobby Video will produce for you. Every clip credits and links its maker.

See more of the trend →
X
A Siamese and a black cat trading lines: the cat version that spread the trendBy @ogfeitoza on X
X
Chewy and Rocky, two chihuahuas, standing up for the duetBy @chewychihuahua_ on X
X
Grandma edition: two grandmothers take over the orange boothBy @AIReelofficial on X

FAQ

Using your own song: answers

Need a hand? Write to us or check the prices.

Can I make the Hotel Lobby AI video with my own song on my phone?

Yes. Open the page in your phone browser, add the two photos, and pick the audio from your files or voice memos. M4A recordings from an iPhone are converted in the browser automatically.

What file types can I upload?

MP3, WAV, M4A (what most phone voice memos save as), AAC or OGG. MP3 uploads unchanged; the others are converted in your browser first. The video uses 2 to 15 seconds, starting where you set the slider.

Is it more expensive to use my own song?

No, audio is free. Only the model, length and resolution set the price: on Wan 3.0 at 480p it is 3, 4, 5, 6 or 7 credits for 5, 8, 10, 12 or 15 seconds.

Is there a free way to do it with my own song?

Not here. Every clip is paid in credits, and your song costs the same as the default track: 6 credits for 12 seconds. Packs start at 10 credits for $9.99, and a failed render refunds automatically.

Can both people sing my song together?

No. Your upload is lip-synced by the lead only; the partner reacts and dances. For two voices swapping lines, use AI rap with Both rap on a Seedance model, or make two clips with the photos swapped and join them, as shown in two people, one song.

Who performs the audio, and what does the other person do?

The lead on the left mouths your audio into the hanging mic. The partner on the right points, reacts and dances on the beat, as in the original routine.

Can I upload the official “Hotel Lobby” recording?

Only if you hold the rights to that recording. To post with the licensed song, add it from the sound library inside TikTok, Reels or CapCut when you publish.

Can the AI write the song for me instead?

Yes. Choose a Seedance model under Video, set the sound to AI rap and type a topic of up to 120 characters. The model writes an original verse and beat; it ignores any upload and is instructed not to copy existing songs.

What if my file is longer than 15 seconds?

That is fine. Any length uploads, but only 2 to 15 seconds is used. Your browser trims the file to the part you choose, which keeps the upload small.

How do I get the cleanest lip-sync?

Use a recording with clear vocals and little background noise, and start the selection on a word rather than on silence. Rap and speech both sync well.

Press play on your track

Make the booth perform your song

Two photos and a short audio file. It costs what the default track costs.