Jump to main content

Voice Note to Hotel Lobby AI Video: Your Words, Lip-Synced

To put your own words in a Hotel Lobby AI video, record them with your phone’s voice recorder, upload the file as Your song on the own song page, slide the orange frame over the bit you want and create. The left performer lip-syncs your recording at the hanging mic while the right one hypes. It runs on Wan 3.0, takes up to 15 seconds of audio and is priced like the Hotel Lobby track: 6 credits for 12 seconds at 480p.

Hotel Lobby Video does not record in the browser, so the voice note has to come from your phone’s own recorder app. Below: how to record it so lip-sync has an easy job, how to get the file into Safari or Chrome, and what the generator is built to do with it.

Last updated

What the generator does with your recording

  1. You choose the file. MP3, WAV and M4A are listed; AAC and OGG open as well. Any length is fine.
  2. You slide the orange frame to the section you want. Its width equals the video length: 5, 8, 10, 12 or 15 seconds on the Hotel Lobby set.
  3. Your browser trims that section and uploads only that. If trimming or converting is needed, it goes up as WAV.
  4. Wan 3.0 animates the left person speaking it, and your recording becomes the soundtrack. The model is told to leave the audio as it is, so your voice is neither cloned nor altered.

Say it in your own voice

Drop your voice note in here

Your song is preselected: add both photos, pick the file and slide the orange frame over the seconds you want.

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

How to record a voice note that lip-syncs cleanly

  • Begin speaking straight away. Silence is not trimmed, and a silent opening shows as a closed mouth.
  • Aim for 15 seconds or less, or record longer and frame the strongest part.
  • Find a quiet room; noise is not removed.
  • Speak a touch slower and clearer than you would on a call.
  • Want a beat? Play it from a second speaker while recording, or mix it in an editor first. It all goes in as a single file.
  • Script it. 12 seconds fits about 25 to 35 spoken words.

Three scripts that fit the length

  • Anniversary: “Five years, one tiny flat, zero arguments about the thermostat. Okay, maybe a few. Happy anniversary, Lena, I would do it all again.”
  • Good luck: “Big day tomorrow, Omar. You studied, you prepped, you even ironed a shirt. Walk in like you own the place. We are so proud of you.”
  • Welcome home: “Back from six months away and the couch still remembers you. Welcome home, Ana, the group chat has been far too quiet!”

Moving the voice note from phone to browser

iPhone

  1. In Voice Memos, select the recording, tap More, then Share, then Save to Files (Apple Support). It is saved as M4A.
  2. In the generator, press Change on the sound row, pick Your song, then Choose file.
  3. Safari shows the Files picker (Recents, Shared, Browse). There is no Voice Memos shortcut, so browse to where you saved it and tap the file.

Android or desktop

Use the Share or Save option in your recorder app to keep the memo as a file, then select it with Choose file. Recorder apps differ between Android phones, so check where yours saves. On a computer, any MP3, WAV or M4A file will do.

Framing the right seconds and creating

  1. Slide the orange frame across the waveform. The label above shows its position, such as “Using 0:00.0 – 0:12.0 of 0:15.3”.
  2. Press Play the part you picked to hear just that section.
  3. If the recording is shorter than the video, the page says how many silent seconds will be left at the end. Pick a shorter length to avoid them.
  4. Put whoever should be speaking in the left slot.
  5. Press Create video. The price matches the Hotel Lobby track.

Realistic expectations for the result

  • Only the left person lip-syncs; the right one hypes. One recording cannot be split between two mouths in one video; two people, one song shows the two-video workaround.
  • Lip-sync tracks the voice, so crisp words help and mumbling or loud music under the voice hurt.
  • Unless you also upload Your clip, the moves are the Hotel Lobby routine.
  • Wan 3.0 is the model that keeps a supplied soundtrack as given, which is why uploaded audio is Wan 3.0-only. Likeness and timing still vary from render to render.
  • Every try is paid; a render that fails is refunded automatically.

Pair the voice note with your own moves

Upload Your clip for the movement and your memo as Your song: the clip sets how you both move, the recording sets what the left person says. Clip prep is covered in using your own reference video.

Upload the voice note

FAQ

Can I record a voice note on my iPhone and make the person in the photo say it?

Yes. Save the Voice Memos recording to Files, upload it as Your song, and the left person in the video lip-syncs it.

Can I record straight into the website?

No. Use your phone’s recorder, save the memo as a file, then upload it as Your song.

Will my voice be changed or cloned?

No. Your recording is used as the soundtrack and the model is told to keep it as it is. Only the face on screen moves to it.

Which file types can I upload?

MP3, WAV and M4A (the iPhone Voice Memos format), plus AAC and OGG. The browser converts what it needs to before upload.

What is the maximum length of the voice note?

The file itself can be any length; the video uses 2 to 15 seconds of it, matching the length you choose.

Can both people say the voice note, and does it cost extra?

Only the left person lip-syncs, so swap the photos and make a second video for the other half. The sound never changes the price: 6 credits for 12 seconds at 480p.

References

Hotel Lobby Video is an independent product with no ties to Quavo, Takeoff, Migos, Quality Control Music, Motown or COLORS.