Sign inGet started
WaveSpeedVideo to videoComing soon

wavespeed-ai/ai-video-editor/talking-head

wavespeed-ai/ai-video-editor/talking-head is a video to video tool from WaveSpeed that runs in the background and returns video. Coming soon: listed with its price, not yet open to runs.

This tool is listed but not yet available to run.

Price pending

Pricing

Price pending.

Limits

Runs
In the background
Returns
video
Longest queue wait
3600s
Run deadline
1800s
Largest inline input
1024 KB
Largest input file
500 MB
Largest output
4768 MB
Outputs per run
16

Input

FieldKindDefaultDescription
videos requiredlist—The talking-head video to edit. Up to 2 hours is processed.
languageone of
auto, en, fr, es, pt, it, ru, zh-CN, zh-TW, ja, ko
autoLanguage spoken in the source video. "auto" detects it; set it when detection is unreliable, for example with heavy accents, background music or very short speech.
aspect_ratioone of
16:9, 9:16, 1:1, 4:5, 5:4, 4:3, 3:4, 3:2, 2:3, 21:9
—Aspect ratio of the output video. Auto-detected from the source video if not specified. Other ratios follow the speaker's face.
caption_styleone of
highlight, plain, none
highlightBurned-in captions. "highlight" lights up each word as it is spoken, "plain" shows static caption lines, "none" adds no captions.

Same request in code

curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "wavespeed",
    "model": "wavespeed-ai/ai-video-editor/talking-head",
    "input": {
      "videos": [
        "<videos>"
      ]
    }
  }'