Listing photos to a narrated tour video with TTS and Timeline
Turn ten listing photos into a 45-second narrated tour: write the script, get word timestamps from TTS, then render stills on a Timeline spine for about $0.15.
Write a script of about 110 words, send it to the TTS Router for narration, then place ten listing photos as stills on a Timeline 1.0 render timed to that audio. The narration costs $0.0475 per 1,000 characters, so a 700-character script is about $0.03, and the render is $0.10 per rounded-up output minute. Total for a 45-second tour: roughly $0.13 to $0.15, before any retries.
Steps
Upload each photo (POST /v1/assets/upload-url, PUT the bytes, then POST /v1/assets/{id}/complete; the ready asset's url is the media.sume.com URL Timeline accepts), because Timeline only accepts this workspace's media. Generate the voice with POST /v1/tts-router/generate and request timestamps: {words: true}; the result carries words[] with start and end seconds. Pick the word that opens each room and use its start as that photo's start time. Photos are static holds, so keep each one on screen for four to six seconds.
Costs
| Step | Rate | Example | Cost |
|---|---|---|---|
| Narration | $0.0475 per 1,000 chars | 700 chars | $0.03 |
| Render | $0.10 per rounded-up minute | 45 s | $0.10 |
| Photo uploads | no generation charge listed | 10 | not priced as a job |
| Plan check | unbilled | 1 | $0.00 |
Timeline body
{
"audio": { "url": "https://media.sume.com/artifacts/artf_demo/tour.mp3", "duration_seconds": 45 },
"video": [
{ "source_url": "https://media.sume.com/artifacts/artf_demo/front.jpg", "start": 0, "duration": 5, "fit": "cover" },
{ "source_url": "https://media.sume.com/artifacts/artf_demo/kitchen.jpg", "start": 5, "duration": 6, "fit": "cover",
"transition": { "type": "fade", "duration": 0.5 } }
]
}Limits
Narration describes what you write, so check every claim about size, price or neighbourhood against the listing. Stills are holds, not camera moves; for motion generate a clip per room with an image-to-video model and expect a higher cost. Coverage may trail the audio spine by at most 0.5 seconds, so make the last photo long enough. Disclose staged or AI-altered images where listing rules require it.
Sources
Related posts
More in Use cases
- Recast a video longer than 30 seconds: trim, recast, rejoin
H3 Max Recast takes 5 to 30 seconds of source. For a 90 second video on Sume, probe it, trim ranges, recast each at 768p, then plan the join. Cost math inside.
- Review a creator clip's transcript before reusing it as a paid ad
Get a creator clip's transcript for $0.01 per audio minute with video inspect, then flag risky claims with your own word list before the clip becomes an ad.
- Run one video prompt across five Sume models: a Python bake-off
Submit the same prompt to five Sume video models, choose each model's resolution from the catalog, and compare cost and time. Runnable code under 30 lines.
- Yearbook slideshow video: photos, narration and music in one render
Build a 90-second class slideshow: 18 photos on a Timeline 1.0 spine with fades, TTS narration, and a Music Router bed. Costs worked out, with limits.
Written by Sume