Veed Dubbing API Documentation

Veed Dubbing API Documentation

Playground

VEED Dubbing Standard translates videos across 86 languages with cloned voices and synchronized lip movements, making it suitable for multilingual localization, global marketing, training, social content, and professional dubbing workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

VEED Dubbing translates spoken content in a video, recreates the translated speech in the speaker’s voice, and synchronizes lip movements with the new dialogue.

Why Choose This?

• 86 languages — Translate speech into a wide range of target languages.
• Voice preservation — Retain the original speaker’s vocal character in the translated speech.
• Lip synchronization — Match visible mouth movements to the translated dialogue.
• Terminology guidance — Add key names and terms to improve recognition and consistency.
• Simple localization workflow — Upload a video, choose a language, and generate the dubbed result.

Parameters

How to Use

1. Upload a video — Provide a video with clear, audible speech.
2. Choose the target language — Select the language for the translated dialogue.
3. Set source language optional — Leave it on auto or choose the spoken language manually.
4. Add keyterms optional — Include important names or terminology when needed.
5. Submit — Generate and retrieve the dubbed video.

Pricing

$0.12 per billed second of input video.

Input duration is rounded up to the next whole second for billing.

Language selection and keyterms do not add separate charges.

Best Use Cases

• Training and educational videos — Localize lessons and instructional content.
• Creator content — Translate spoken videos for multilingual audiences.
• Product demonstrations — Dub product walkthroughs and presentations.
• Marketing videos — Adapt campaign content for different languages.
• Business presentations — Create localized versions of internal or external communications.

Pro Tips

• Use videos with clear speech and minimal background noise.
• Keep faces well lit and clearly visible for better lip synchronization.
• Specify the source language when automatic detection may be uncertain.
• Add important names, brands, and technical terms as keyterms.
• Review translated speech and terminology before publishing.

Notes

• Input videos must be no longer than 10 minutes.
• The source video must contain audible speech.
• Select a supported base language. Separate regional accents are not available.
• Up to 10 keyterms are supported.
• Each keyterm can contain up to 50 characters and 5 words.
• Keyterms must not contain <, >, {, }, [, ], or backslashes.
• Keyterms guide speech recognition and terminology preservation; they are not source-to-translation pairs.

Related Models

• VEED Dubbing Standard — Translate and dub videos with voice preservation and lip synchronization.
• VEED Dubbing Pro — Use the Pro dubbing workflow for higher-end video localization.

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": "af",
  "source_language": "auto"
}
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/veed/dubbing" \
  -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

Response Parameters

Result Request Parameters

Result Response Parameters