Kling Avatar output length follows audio; Sume H3 Max is 5-14.8 s
On fal, Kling Avatar v2 Pro output duration matches the audio file. On Sume the audio sets length too, within route windows from 5 to 14.8 s up to 60 s.
On fal, the output duration of Kling AI Avatar v2 Pro matches the length of the audio file, and you pay per output second. Sume works the same way for its still-plus-audio routes, but each route has its own window: 5 to 14.8 seconds on MiniMax H3 Max lip sync, and a 4 to 60 second estimate for Avatar Video scripts.
fal facts are from its Kling AI Avatar v2 Pro page, read 2026-10-01. Sume facts are from the Models overview and Generate avatar video.
What does fal say about duration?
The page states "Output Duration: Matches audio length" and that video is scaled to the audio file's duration. It prices Pro at $0.115 per second of output, so the audio file you upload is also your cost driver. The snapshot gives no maximum audio length.
What are the Sume windows?
Three Sume routes are relevant, and the length is set differently on each.
| Route | Input | Length rule |
|---|---|---|
POST /v1/minimax/h3-max/lip-sync | Still + audio | Audio 5 to 14.8 s |
POST /v1/veed/fabric-1.0 | Still + audio (audio_url, duration_seconds) | Set by the audio you send; the alias table lists duration_seconds 1 to 300 |
POST /v1/avatar-1.0/talking-video | Avatar + script or video_inputs | Accepted when estimated at 4 to 60 s inclusive |
What happens with audio outside the window?
For Avatar Video, the docs say to shorten longer scripts or split them into multiple jobs. For H3 Max, keep each audio file inside 5 to 14.8 seconds, so cut longer narration into segments first; the approach is in lip-sync for clips longer than 15 seconds.
Which route should I pick for a given length?
For a short spoken line, the audio length decides: under 5 seconds is outside the H3 Max window, so use Fabric. For a script you have not recorded yet, Avatar Video takes text and estimates duration for you. For long audio, compare Fabric's cap with other vendors in HeyGen audio-to-video limits versus Sume Fabric.
Sources
Related posts
More in Models
- Kling Avatar v2 Standard vs Pro: fal tiers vs Sume quality
fal prices Kling Avatar v2 Pro at $0.115/s and Standard at $0.0562/s. Sume Avatar Video has its own quality values: standard, plus and max.
- MiniMax H3 Max reference audio needs an image or video on Sume
Krea says MiniMax H3 Max audio references cannot be sent alone; Sume's reference_audio_urls has the same rule. Limits for images and videos compared.
- Wan 3.0 references or start/end frames, not both: two Sume calls
Krea says a Wan 3.0 job takes reference media or start/end frames, not both. Sume lists them as separate modes, so split the work into two requests.
- LTX-2.5 Cinemagraph LoRA vs image-to-video on Sume
The LTX-2.5 Cinemagraph LoRA is an image-to-video adapter for selective motion. On Sume, start from first_frame and describe the motion in the prompt.
Written by Sume