Topaz Video Frame Interpolation API Documentation

Topaz Video Frame Interpolation API Documentation

Playground

Try it on WaveSpeedAI!

Topaz Video Frame Interpolation increases video frame rates and creates smooth slow motion using Topaz Apollo, Chronos, and Aion models, making it suitable for sports footage, cinematic slow motion, animation, restoration, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Topaz Video Frame Interpolation generates intermediate frames for frame-rate conversion and slow-motion video.


Why Choose This?

  • Frame interpolation — Create intermediate frames for frame-rate conversion.
  • Model selection — Choose from the available processing models.
  • Resolution options — Select an output resolution tier.
  • Frame rate and slow motion — Select output FPS and a slow-motion factor.

Parameters

ParameterRequiredDescription
videoYesThe video to process.
modelNoProcessing model. Options: Apollo, Apollo Fast, Chronos, Chronos Fast, Aion. Default: Apollo.
resolutionNoThe resolution to process and output the video at. The source aspect ratio is preserved. Options: 720p, 1080p, 2k, 4k. Default: 1080p.
fpsNoOutput frame rate. The source is read at 30 fps. Options: 30, 48, 50, 60, 120. Default: 60.
slowmoNoSlow-motion factor: 2 doubles the duration, 4 quadruples it. 1 keeps the original speed. Options: 1, 2, 4, 8. Default: 1.

How to Use

  1. Upload your video — Provide a file or URL.
  2. Choose a model — Select the processing option for your input.
  3. Select a resolution — Choose the desired output tier.
  4. Set motion options — Choose output FPS and slow-motion factor.
  5. Submit — Process and download the result.

Pricing

Pricing is calculated upfront from the source video duration and selected resolution and processing model. Output FPS and slow-motion factor also affect the price. The source duration is rounded up to the next whole second, capped at 300 seconds for billing. The minimum charge is $0.10, and the total is rounded up to the next $0.10.

Example Costs

For a 10-second source video with fps=60 and slowmo=1:

Model720p1080p2k4k
Apollo / Chronos$0.10$0.20$0.30$0.60
Apollo Fast / Chronos Fast$0.10$0.10$0.20$0.30
Aion$0.20$0.40$0.70$1.50

Examples use the selected resolution and a billing basis of 30 source frames per second. Other durations or motion settings have different totals; the displayed price is calculated before submission.


Notes

  • Use source clips up to 300 seconds.
  • The source aspect ratio is retained when selecting a resolution.
  • slowmo=1 keeps the original speed; higher values extend playback duration.
  • The price depends on both output FPS and the slow-motion factor.

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",
  "model": "Apollo",
  "resolution": "1080p",
  "fps": 60,
  "slowmo": 1
}
JSON
)

# 1. Submit the prediction once. Never retry this request automatically:
# a retry after an unclear failure can create a second, billed task.
CHECK='The task may already exist. Check History or the predictions list before submitting again.'
if ! SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --connect-timeout 10 --max-time 60 \
  -X POST "https://api.wavespeed.ai/api/v3/topaz/video/frame-interpolation" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}"); then
  printf 'Submit failed. %s\n' "${CHECK}" >&2
  exit 1
fi

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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id. %s\n' "${CHECK}" >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction reaches a final status.
BODY_FILE=$(mktemp)
trap 'rm -f "${BODY_FILE}"' EXIT
while true; do
  # Transient errors (429, 5xx) are retried, honoring Retry-After.
  HTTP_CODE=$(curl --silent --show-error --fail-with-body \
    --connect-timeout 10 --max-time 60 --retry 5 --retry-delay 2 \
    --output "${BODY_FILE}" --write-out '%{http_code}' \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}" || true)
  case "${HTTP_CODE}" in
    2??) ;;
    000|429|5??)  # dropped connection or temporary error: keep polling
      printf 'Task %s: HTTP %s, polling again in 10s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      sleep 10; continue ;;
    *) printf 'Task %s: HTTP %s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      cat "${BODY_FILE}" >&2; exit 1 ;;
  esac
  RESULT=$(jq 'if type == "object" and has("data") then .data else . end' "${BODY_FILE}")
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

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

Retry temporary errors only while polling, never the submit request. Errors, retries and timeouts

Parameters

Task Submission Parameters

Request Parameters

ParameterTypeRequiredDefaultRangeDescription
videostringYes-The video to process.
modelstringNoApolloApollo, Apollo Fast, Chronos, Chronos Fast, AionThe Topaz model to use. Apollo: Precision slow motion and frame rate conversion (default). Apollo Fast: Faster Apollo for simpler motion. Chronos: Natural slow motion for real-world motion. Chronos Fast: Faster Chronos for time-sensitive work. Aion: Extreme slow motion for complex, high-resolution motion.
resolutionstringNo1080p720p, 1080p, 2k, 4kThe resolution to process and output the video at. The source aspect ratio is preserved.
fpsintegerNo6030, 48, 50, 60, 120Output frame rate. The source is read at 30 fps.
slowmointegerNo11, 2, 4, 8Slow-motion factor: 2 doubles the duration, 4 quadruples it. 1 keeps the original speed.

Every model also accepts the global request options enable_sync_mode and enable_base64_output; see their pages for details.

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.