Podcast trailer clip at 480p: 15 seconds on Wan, H3 or Seedance

A 15-second clip at 480p costs $0.94 on wan-3.0, $0.94 on minimax-h3 and $2.11 on seedance-2-fast. These three accept an audio reference, so the trailer can carry an excerpt of your episode instead of a generated soundbed. Source: Video generation, read 2026-10-06.

480p is enough for a waveform-and-host animation that will sit in a social feed. Move to 720p if the clip will be played full screen.

What does the 15 seconds cost?

Fifteen seconds at the lowest rung each model lists.

How do I add the episode excerpt?

Send it as an audio_url in input_references.

curl -sS -X POST https://api.sume.com/v1/videos \
  -H "Authorization: Bearer $SUME_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wan-3.0",
    "prompt": "Two hosts at microphones, warm studio, slow push-in, audio waveform glowing behind them",
    "duration": 15,
    "resolution": "480p",
    "aspect_ratio": "16:9",
    "input_references": [
      {"type": "audio_url", "audio_url": {"url": "https://example.com/episode-excerpt.mp3"}}
    ]
  }'