A 90-second avatar product video: two 45-second jobs, $0.22 to join

Sume's avatar video route accepts scripts it estimates at 4 to 60 seconds, so a 90-second presenter video is two jobs of about 45 seconds joined on Timeline 1.0. The join costs $0.22 beyond the avatar jobs: 2 audio detaches at $0.01 plus a render of 90 seconds, which bills 2 minutes at $0.10 (read 2026-10-08).

What the avatar route allows

POST /v1/avatar-1.0/talking-video takes an avatar_handle and either a script or ordered video_inputs, never both. Sume rejects longer plans, so make the script shorter or split it. aspect_ratio supports 1:1, 3:4, 9:16, 4:3 and 16:9, with 9:16 as the default, and resolution is 720p. Quality is standard, plus (default) or max.

Split at a natural pause

Cut the script where the presenter would breathe, such as between the problem and the demo. Use the same avatar_handle, aspect_ratio and scene direction in both jobs, because one final video expects one avatar and one shared scene, and two jobs that differ will show a jump at the join. A voice.type: silence beat in video_inputs is available for a pause inside one job.

Joining the two outputs

A Timeline render needs an audio spine. Detach each avatar clip's audio with POST /v1/audio-detach ($0.01 per job), then pass both files as audio.parts[] in one render; parts join gaplessly with no re-synthesis. The two avatar MP4s become two video[] slots whose start values follow the part lengths.

{
  "audio": { "parts": [
    { "url": "https://media.sume.com/artifacts/artf_demo/part1.wav" },
    { "url": "https://media.sume.com/artifacts/artf_demo/part2.wav" } ],
    "duration_seconds": 90 },
  "video": [
    { "source_url": "https://media.sume.com/artifacts/artf_demo/part1.mp4", "start": 0, "duration": 45 },
    { "source_url": "https://media.sume.com/artifacts/artf_demo/part2.mp4", "start": 45, "duration": 45 }
  ],
  "output": { "width": 720, "height": 1280 }
}

Captions on a 90-second result

Inline captions on the avatar job burn into each part and are priced inside the avatar estimate, which this post does not quote. Standalone captions cover videos of up to 60 seconds at $0.20, so a joined 90-second file is outside that fixed price; caption each part before the join, or check the live rate in GET /v1/catalog.