AI Video Editor Video Translator API Documentation

AI Video Editor Video Translator API Documentation

Playground

AI Video Translator dubs any video into 28 languages: every speaker keeps a voice that matches their own, the original music and sound effects stay under the dub, and the timing follows the picture. Translated subtitles come as an SRT file with every result. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

AI Video Translator translates and dubs videos into 28 target languages while preserving the original picture. It generates speech designed to resemble each speaker’s voice and fits translated dialogue to the original timing. Keep or remove background audio, specify translations for names and terms, and get translated subtitles with every result.

Why It Stands Out

• 28 target languages: English, Spanish, French, German, Italian, Portuguese, Dutch, Swedish, Danish, Norwegian, Finnish, Greek, Russian, Polish, Turkish, Hebrew, Indonesian, Malay, Vietnamese, Thai, Filipino, Swahili, Chinese (Simplified and Traditional), Japanese, Korean, Arabic and Hindi.
• Speaker-aware dubbing: automatically detect speakers or specify the number of people speaking.
• Voice matching: generate translated speech designed to resemble each speaker’s original voice.
• Background audio control: keep the original music and sound effects, or remove them for a voice-focused result.
• Timing-aware translation: fit translated dialogue to the timing of the original speech.
• Custom terminology: use glossary to specify translations for names, brands and other terms.
• Subtitles included: every result comes with an SRT file of the translated lines.
• Original picture preserved: retain the source video’s picture, frame rate and resolution.

Parameters

How to Use

1. Upload a video or provide its URL.
2. Select a target_language different from the language spoken in the video.
3. Leave source_language on auto, or specify the source language.
4. Leave speakers empty for automatic detection, or select the number of speakers.
5. Choose whether to keep background audio and optionally add glossary entries.
6. Submit the request and download the dubbed MP4, plus the SRT subtitle file.

Pricing

$0.25 per minute of source video, rounded up to the next whole minute. Billing is capped at 120 minutes per video.

Price = source duration in minutes, rounded up × $0.25, subject to the 120-minute cap.

Target language, speaker count, background audio settings, glossary entries and subtitles do not add separate charges.

Notes

• Billing uses the source video duration, not the length of the translated speech.
• Up to 2 hours of video is processed per request.
• The target language should differ from the language spoken in the source video.
• Leave speakers unset for automatic detection; do not use 0 to request automatic detection.
• Add one glossary entry per array item, using source=translation.
• Subtitles come as a separate SRT file; they are not burned into the picture.
• The dubbed MP4 retains the original picture, frame rate and resolution; it does not alter mouth movements to match the translated speech.
• Translation accuracy, voice similarity and background audio separation can vary with recording quality, noise and overlapping speech.

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",
  "target_language": "en",
  "source_language": "auto",
  "speakers": 1,
  "background": "keep"
}
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/wavespeed-ai/ai-video-editor/video-translator" \
  -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

Parameters

Task Submission Parameters

Request Parameters

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

Response Parameters

Result Request Parameters

Result Response Parameters