Vacation rental check-in video for guests with AI voice
Replace a long check-in message with a 60-second Sume video: door, Wi-Fi, parking and house rules in photos and a TTS voice for about 13 cents.

To make a check-in video for vacation-rental guests, photograph each step (the street sign, the lockbox, the door, the Wi-Fi card, the parking spot), write one sentence per photo, and join them on Sume with a text-to-speech voice and a Timeline render. A 60-second video with about 900 characters of script costs about $0.14: $0.043 for the voice and $0.10 for one rendered minute. The same video with a talking avatar would be $11.04 at Standard rates.
Why a video instead of a longer message?
Guests arrive tired and often read only the first lines of a message. A video of the path from the street to the door answers the question that causes late-night calls: which door, which box, which code. It is also the same file for every guest, so the cost is paid once per property, not once per stay.
What goes in the 60 seconds?
Keep to the sequence a guest actually walks. Use real photos, because a generated hallway will not match your hallway.
- Street and parking: 8 seconds, one photo each.
- Lockbox and door: 10 seconds, with the lock closed-up.
- Wi-Fi, heating or air conditioning, and hot water: 15 seconds.
- House rules, quiet hours and bins: 15 seconds.
- Who to call, and when: 7 seconds.
How do I keep the door code out of the video?
Do not say or show the code. A video file is easy to forward and lives on your hosting for as long as you keep it. Say 'the code is in your booking message' and send the code separately. Use the same rule for the Wi-Fi password: show the card, never read the characters aloud. If a rule changes, edit one sentence, regenerate the voice and render again.
What does it cost, and how do I add captions?
Voice is $0.0475 per 1,000 characters, and Timeline is $0.10 per rounded-up output minute. A portfolio of ten properties is ten voices and ten renders, about $1.43. For captions, send authored cues to the standalone video-captions endpoint, which burns overlay text without speech recognition; its rate is not on the pricing page, so check it in the playground first. Captions help guests who play the clip with sound off, and guests who read a second language.
| Route | Rate | 60-second cost |
|---|---|---|
| Photos + TTS + Timeline render | $0.0475 per 1,000 characters, $0.10 per minute | about $0.14 |
| Avatar, Standard | $0.184 per second | $11.04 |
| Avatar, Plus | $0.245 per second | $14.70 |
Sources
Related posts
More in Use cases
- Valentine's Day 2027 is a Sunday: four order-by cues, $1.43
Valentine's Day 2027 is Sunday Feb 14. Render one 5-second clip and burn four dated reminder cue sets from January 11 to Feb 12 for about $1.43 on Sume.
- Veterans Day offer clip for a small shop: 5 seconds, $0.825
Make a Veterans Day offer clip for Wed Nov 11, 2026 from your storefront photo: Wan 3.0 at 720p plus burned-in terms as caption cues, $0.825 on Sume.
- Voice actor or AI voice for a 30-second ad? What an API covers
Hire a voice actor or use AI text to speech for a 30-second ad: what Sume's TTS API does, what it cannot do, and the $0.315 audio bill for three takes.
- AI album cover generator: square art at 3000×3000
Generate square album art, then upscale: Apple recommends at least 3000×3000. On Sume, generate 2400×2400 and upscale it 1.25× to reach 3000×3000.
Written by Sume