LTX-2.5 48 fps option: conform frame rate on Sume
LTX-2.5 offers 24/25 fps or 48/50 fps. Sume's video catalog has no fps field, but Timeline output.fps conforms a clip to 24, 25, 30 or 60.

LTX-2.5 runs at 24 or 25 fps as standard, with 48 or 50 fps as an option, according to the launch summary. On Sume you do not pick a frame rate at generation time; you conform it afterwards with Timeline 1.0's output.fps, which accepts 24, 25, 30 or 60.
What the launch summary says
The same page describes native multi-shot output in one pass and a new diffusion video decoder. I am only relying on the frame rate and multi-shot points here.
What Sume exposes
Each entry in GET /v1/videos/models lists resolutions, aspect ratios, durations, frame image and reference support, audio and seed. There is no frame-rate field, so there is nothing to set per request on POST /v1/videos.
| Surface | Frame rate control |
|---|---|
| POST /v1/videos | None advertised in the catalog |
| Timeline 1.0 render | output.fps: 24, 25, 30 or 60 |
| Timeline 1.0, fps omitted | Matches the sources; 30 only if nothing has a rate |
Conform a clip
Timeline needs an audio spine with a declared length and Sume-hosted clips. Import first, then render one slot. For a silent clip, use audio.mode: "silence".
curl -X POST https://api.sume.com/v1/timeline-1.0/render \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: conform-001" \
-d '{
"audio": { "mode": "silence", "duration_seconds": 8 },
"video": [{ "source_url": "https://media.sume.com/artifacts/artf_demo/clip.mp4", "start": 0, "duration": 8 }],
"output": { "fps": 24 }
}'The catch
A rate that differs from the source's is met by repeating or dropping frames, so motion can judder, and the job reports output_fps_resamples_sources. That means a 48 fps source forced to 24 or 30 is decimated, and 48 cannot be requested at all because 60 is the nearest option. Public rate is $0.10 per ceil output minute; confirm live in GET /v1/catalog.
Sources
Related posts
More in Media tools
- Lyria 3.5 output: MP3 or WAV at 44.1 kHz, and what Sume returns
Google lists MP3 by default or WAV, 44.1 kHz stereo, with a SynthID watermark. Sume's music docs say the artifact is typically audio/mpeg. Check it in code.
- Lyria 3.5 prompts: [Verse] tags or [0:00-0:30] time ranges?
Google's Lyria 3.5 docs show [Verse], [Chorus] and [Bridge] tags. Sume's music docs show time-range markers. What each says, and how to test both on one brief.
- MAI-Voice-2.1 Flash narration for a video cut
Narration from any voice model can be the audio spine of a Sume Timeline cut. Import the file first, then render at $0.10 per output minute.
- Mercado Libre Clips: 61 s needs two clips in Timeline
Mercado Libre Clips run 10 to 61 seconds. Some Sume models make 30 s clips, so two in Timeline give a 60 s vertical Clip for one billed minute.
Written by Sume