Video Restorer API Documentation

Video Restorer API Documentation

Playground

Try it on WaveSpeedAI!

Video Restorer cleans up damaged footage: strip compression artifacts from low-bitrate video or bring out-of-focus footage back into sharp focus, keeping the subject, framing and motion exactly as they are. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Fix damaged footage without touching the content. Video Restorer has two modes: decompress strips the macroblocking, ringing, banding and chroma bleed left by low-bitrate encodes, and deblur brings soft, out-of-focus footage back into sharp focus. Subject, framing and motion stay exactly as they are; only the image quality changes.


Two Modes

  • decompress (default) For clips that were re-encoded at a low bitrate: social-media downloads, old phone footage, screen recordings. Restores clean edges and fine detail and removes block artifacts.

  • deblur For footage that is soft or out of focus. Recovers sharp focus and crisp detail. It targets defocus blur, not motion blur, and heavily destroyed detail is reconstructed rather than recovered.


Parameters

ParameterRequiredDescription
videoYesInput video (URL or upload). Up to 2 minutes is processed.
modeNodecompress (default) or deblur
promptNoShort description of the scene; leave empty for a generic restore
target_resolutionNoOutput resolution: 480p, 720p, 1080p (default: 720p). Aspect ratio is preserved.
seedNoSeed for reproducible results

Pro Tips

  • Pick the mode that matches the damage: blocky, smeared colors and edge ringing means decompress; uniformly soft focus means deblur.
  • Neither mode is an upscaler or a denoiser. For resolution, run the result through a video upscaler afterwards.
  • Keep the same seed to reproduce a result.

Limits and Performance

  • Max clip length per job: 2 minutes (longer input is truncated)
  • Processing speed: roughly 8 seconds of wall time per second of video at 720p, about 20 seconds per second at 1080p

Pricing

> Billing duration: Input media duration is rounded up to whole seconds. The minimum billed duration is 3 seconds; shorter inputs are billed as 3 seconds. Input beyond 2 minutes is not processed and not billed.

Per-second billing with a 3-second minimum. The table below lists prices per 5 seconds for easy comparison.

Output ResolutionCost per 5 seconds
480p$0.10
720p$0.20
1080p$0.50

Billing Rules

  • Minimum charge: 3 seconds
  • Per-second rate = (price per 5 seconds) ÷ 5
  • Billed duration = video length in seconds (rounded up), with a 3-second minimum, capped at 120 seconds
  • Total cost = billed duration × per-second rate (by output resolution)

Notes

  • Video is the only required field.
  • Maximum processed video length per job: 2 minutes.
  • Ensure video URLs are publicly accessible.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
  "mode": "decompress",
  "target_resolution": "720p"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/video-restorer" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

ParameterTypeRequiredDefaultRangeDescription
videostringYes-The video to restore; up to 2 minutes is processed (longer input is truncated).
modestringNodecompressdecompress, deblurdecompress: remove compression artifacts (macroblocking, ringing, banding, chroma bleed) from low-bitrate footage. deblur: bring soft, out-of-focus footage back into sharp focus (defocus blur only, not motion blur).
promptstringNo-Optional. A short description of what the video shows (for example "a woman walking a dog in a park at sunset"). Helps the model keep the right details; leave empty for a generic restore.
target_resolutionstringNo720p480p, 720p, 1080pOutput resolution. The input aspect ratio is preserved; output is never larger than the input.
seedintegerNo--The seed for random number generation. Omit for a random seed.

Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
data.idstringUnique identifier for the prediction, Task Id
data.modelstringModel ID used for the prediction
data.outputsarrayOutput values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.statusstringTask status. completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses.
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds

Result Request Parameters

ParameterTypeRequiredDefaultDescription
idstringYes-Task ID

Result Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
dataobjectThe prediction data object containing all details
data.idstringUnique identifier for the prediction
data.modelstringModel ID used for the prediction
data.outputsarray<string | object>Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model.
data.urlsobjectObject containing related API endpoints
data.statusstringStatus: completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses
data.created_atstringISO timestamp of when the request was created
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds
© 2026 WaveSpeedAI. All rights reserved.