Elevenlabs Dubbing API Documentation

Elevenlabs Dubbing API Documentation

Playground

ElevenLabs Dubbing automatically translates and dubs video/audio content into different languages while preserving the original speakers’ voices. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

ElevenLabs Dubbing automatically translates and dubs video or audio content into different languages. Upload your content, select target language — the model transcribes, translates, and generates natural-sounding speech in the target language while preserving the original voice characteristics and timing.

REST inference API, best performance, no cold starts, affordable pricing.

Why Choose This?

• Automatic translation and dubbing End-to-end pipeline: transcription → translation → voice synthesis in one step.

• Voice preservation Maintains the original speaker’s voice characteristics in the dubbed output.

• Multi-language support Supports English, Spanish, French, German, Italian, Portuguese, Chinese, Japanese, Korean, and more.

• Auto language detection Automatically detects the source language, or manually specify for better accuracy.

• Video and audio support Works with both video files and audio-only content.

Parameters

Note: Either video or audio is required (upload one of them).

How to Use

1. Upload your content — video or audio file (choose one).
2. Select target language — the language you want the content dubbed into.
3. Select source language (optional) — choose Auto for automatic detection, or specify manually.
4. Run — submit and download the dubbed content.

Pricing

$0.01 per second of source media, rounded up to the next whole second.

Billing Rules

• Billed by the duration of the source media, prorated per second — no rounding up to whole minutes
• If both video and audio are provided, only video is processed and billed
• Maximum billed duration is 15 minutes; longer content is trimmed to the first 15 minutes
• source_lang, target_lang and the other options do not affect pricing

Supported Languages

source_lang and target_lang take an iso639-1 or iso639-3 language code, not a language name — send es, not Spanish. source_lang also accepts auto (the default) to detect the source language automatically.

The two lists are not the same. A language you can dub from is not always a language you can dub into — Hebrew, Persian and Thai are supported sources but not targets, while Filipino is a supported target but not a source. Both lists below were verified against the live API.

Target languages (33)

Source languages (57, plus auto)

Best Use Cases

• Content Localization — Translate videos and podcasts for international audiences.
• Marketing — Dub promotional content into multiple languages.
• Education — Make educational content accessible in different languages.
• Social Media — Reach global audiences with multilingual video content.
• Corporate Communications — Translate internal videos and training materials.

Pro Tips

• Use clean, high-quality source audio for best dubbing results.
• Specify source language manually if auto-detection is inaccurate.
• Shorter clips process faster — split long content for parallel processing.
• Content with clear speech and minimal background noise produces better results.

Notes

• Either video or audio is required — upload one of them.
• If both video and audio are provided, the model will process video only.
• Maximum duration is 15 minutes per job; longer content is automatically trimmed to the first 15 minutes.
• For longer content, split into segments and process separately.

Related Models

• ElevenLabs Voice Changer — Transform audio into speech with a different voice.
• ElevenLabs Text-to-Speech — Generate speech from text with natural-sounding voices.
• OpenAI Whisper — Transcribe audio to text with high accuracy.

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'
{
  "target_lang": "ar",
  "source_lang": "auto",
  "num_speakers": 0,
  "drop_background_audio": false
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/elevenlabs/dubbing" \
  -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

Response Parameters

Result Request Parameters

Result Response Parameters