Score travel and drone footage with three moods and one concat
Make three Lyria 3.5 cues for a travel reel, join them with Timeline audio concat at $0.01, and render under drone footage. About $0.69 for 3 minutes.

A travel reel scored with a single loop feels flat. Splitting it into three moods, such as arrival, exploration and sunset, gives the edit a shape. Google's own launch post for Lyria 3.5, read on 2026-10-05, says the model arrived in the Gemini app and API on September 4, 2026 and lists backing tracks among its uses. On Sume you reach it through the Music Router, $0.125 per accepted generation.
Plan
- Arrival: gentle acoustic guitar and soft pads, unhurried, wide and airy.
- Exploration: lifted tempo around 110 BPM, hand percussion and bright strings.
- Sunset: slow, warm, piano and ambient texture, ending on a long fade.
Join and render
Join the three tracks with a Timeline audio concat job: up to 20 parts, wav or mp3 output, flat $0.01 per job. Then use the joined file as the soundtrack.url in a Timeline 1.0 render with fade_out_seconds for the final tail, up to 10 seconds. Drone footage usually has no voice, so duck_db stays at its default 0, a static bed, and gain_db can sit near 0.
| Step | Count | Unit price | Subtotal |
|---|---|---|---|
| Music generation | 3 | $0.125 | $0.375 |
| Audio concat | 1 | $0.01 | $0.01 |
| Render, 3 output minutes | 3 | $0.10 | $0.30 |
| Total | $0.685 |
Matching cuts to moods
Cuts that change scenes sit best on a change of cue. Because the joined file's cue lengths depend on what each take returns, listen to the three takes before you lock the picture and trim the footage to them, not the other way around.
Sources
Related posts
More in Use cases
- Blog post to a 45-second Short that is not the article aloud
Reading an article over stock clips is the pattern YouTube warns about. Pull one claim, add your own angle, and build the Short with Sume Timeline.
- Turn a help article into a 45-second avatar script and render it
Cut a help article to one task of about 100 words and render it as a Sume avatar clip. A 45-second Standard clip is $8.28; the article stays the truth.
- 20 product clips in Spanish and French: 40 caption jobs, $8.00
Index-Translate has a free public API, and Sume burns authored caption cues for $0.20 a job: 20 product clips in 2 languages is 40 jobs and $8.00.
- 2-minute AI video from Kling 3: eight 15 s jobs, $16.80 or $25.20
Kling 4.0 says repeated extension to 2 minutes is coming. On Sume, eight chained kling-3 jobs of 15 s reach 120 s today: $16.80 silent, $25.20 with audio.
Written by Sume