by ElevenLabs

Dub a recording or a video's soundtrack into 33 languages, up to 15 minutes

elevenlabs/dubbing/video-translate
  • Video Translator
  • Audio Translator

About ElevenLabs Dubbing

ElevenLabs Dubbing translates the speech in a recording or a video into one of 33 languages and voices it again. It takes sources up to 15 minutes, can tell up to 32 speakers apart and keeps the background sound unless you turn that off. Audio comes back as an MP3; video keeps its picture and gets the new soundtrack.

Call it with the model name elevenlabs/dubbing/video-translate on POST /jobs/createTask, from $0.012.

Introduction

ElevenLabs Dubbing API for video translation

ElevenLabs Dubbing API replaces a video’s spoken soundtrack with translated speech and returns an MP4 with its original picture. Choose this endpoint for a product walkthrough, recorded lesson, or narrated clip up to 15 minutes when the filmed image should stay intact.

ElevenLabs says its dubbing tool retains speakers’ voice characteristics across languages. This video workflow does not animate mouths or create subtitles, so plan those delivery requirements separately.

Create a translated video task

Use elevenlabs/dubbing/video-translate as the public model name and place the source in video_url.

{
  "model": "elevenlabs/dubbing/video-translate",
  "input": {
    "video_url": "https://example.com/english-product-demo.mp4",
    "target_language": "es",
    "source_language": "en",
    "speaker_count": 1,
    "keep_background_audio": true
  }
}

The example translates a single presenter’s English speech into Spanish while retaining background sound. Substitute a video you have permission to dub, and remove speaker_count if you prefer automatic detection.

Retrieve the MP4 asset

A successful task returns the translated video as an MP4 asset in the task result. Query GET /api/v1/jobs/recordInfo?taskId=<taskId> with the returned task identifier and your authentication, and check for succeeded before using its download URL.

{
  "code": 200,
  "data": {
    "taskId": "<taskId>",
    "state": "succeeded",
    "output": {
      "assets": [
        {
          "url": "https://example.com/spanish-product-demo.mp4",
          "mime": "video/mp4"
        }
      ]
    }
  }
}

This abbreviated response uses a placeholder URL. Inspect the downloaded MP4 for speech and picture together.

Video inputs and language choices

The video endpoint accepts one source plus the language, cast, and background settings shown below.

FieldSupported settingEffect on this request
video_urlVideo source up to 15 minutesSupplies the picture and spoken soundtrack
target_language33 target choices; en by defaultDetermines the translated speech language
source_language57 source choices or autoSpecifies the speech language or requests detection
speaker_countInteger 1–32, or omittedSupplies a known cast size or requests detection
keep_background_audioRetain music and ambienceKeeps background sound beneath translated voices

A source exceeding 15 minutes is rejected when submitted. For a longer training recording, divide it at lesson boundaries and keep the parts organized for review and later assembly.

Picture preservation and workflow choice

This endpoint keeps the picture and changes the soundtrack, with no lip-sync change and no subtitle output. The distinction matters for talking-head footage: the visible mouth continues its recorded movements even when the voice uses another language.

WorkflowInput and outputReason to choose it
ElevenLabs Dubbing audio-to-audioAudio to dubbed MP3A podcast, narration, or voice note
ElevenLabs Dubbing video-translateVideo to dubbed MP4Translated speech with the picture retained
HeyGen Video TranslateVideo translation with lip movementA delivery that needs lip movement
Video Translator V1Video translationAnother option for a video source

These alternatives were not measured in our ElevenLabs tests.

What our video test established

Our 6.04-second English video returned a 6.04-second MP4 after about 14.8 seconds of processing. The result had a new mono AAC audio track, and its video stream was byte-identical to the source.

That byte comparison supports picture preservation for the tested clip. It does not measure translation accuracy across languages, establish processing time for longer videos, or demonstrate changed lip movements.

Prepare, review, and resolve problems

Review the translated speech against the source’s meaning and visible context before publishing a dubbed clip. For example, a product lesson should retain the intended feature names and instructions even though the spoken language changes.

  1. Confirm rights to the footage, its speech, and any music, with agreement from the recorded speakers.
  2. Choose a representative excerpt with the speaker changes or terminology you need to assess.
  3. Specify the target language and a known source language, or use source detection.
  4. Set the cast count when known and decide whether the existing ambience belongs in the dub.
  5. Watch the completed MP4 while checking speech meaning, background balance, and the unchanged lip movement.

An overlong video or speaker count outside 1–32 needs correction before another submission. For an unsuccessful task, inspect the task error details and verify its inputs rather than assuming the download contains a completed dub.

Use the audio sibling when a standalone MP3 is the required delivery. Keep a separate captioning plan for subtitles, and never use a translated voice to impersonate a real person.

Request parameters

ParameterRequiredDescription
keep_background_audioNoKeep the original music and sound effects under the dub; turn off for voices only. Default: true
source_languageNoThe language spoken in the clip. Auto detects it; pick it when music, a strong accent or long pauses confuse detection. auto · af · ar · hy · az · be · bs · bg · ca · zh · hr · cs · da · nl · en · et · fi · fr · gl · de · el · he · hi · hu · is · id · it · ja · kn · kk · ko · lv · lt · mk · ms · mi · mr · ne · no · fa · pl · pt · ro · ru · sr · sk · sl · es · sw · sv · tl · ta · th · tr · uk · ur · vi · cy · Default: auto
speaker_countNoHow many people speak, 1 to 4. Leave empty to detect it. 1–32
target_languageNoThe language to dub into. It must differ from the language in the clip. ar · bg · zh · hr · cs · da · nl · en · fil · fi · fr · de · el · hi · hu · id · it · ja · ko · ms · no · pl · pt · ro · ru · sk · es · sv · tl · ta · tr · uk · vi · Default: en
video_urlYesThe clip to work on.

Pricing

Prices are in USD and charged to your PopNow balance. When a task is accepted, we reserve the maximum quoted amount from your API balance. On completion, we charge for actual usage, never more than the hold, and release the remainder. If the task fails, the hold is released.

OptionUSD per second
Standard$0.012

Send the same request body to POST /jobs/quote to see the estimated and maximum USD charge before running. A quote does not run the task or charge your balance.

API quick start

Call the ElevenLabs Dubbing API in three steps

  1. Create an API key. Sign in to PopNow and create a key in the API console. Keys start with sk-popnow-. API calls are billed in USD from your PopNow balance.
  2. Send the request. POST /jobs/createTask with model elevenlabs/dubbing/video-translate and an input object that follows the parameter table. The response returns a task ID straight away.
  3. Get the result. Poll GET /jobs/recordInfo with the task ID, or pass a callBackUrl and we post the result to it. Download the output links when the task succeeds.
# 1. Create the task. Keep the Idempotency-Key if you retry after a network error.
export IDEMPOTENCY_KEY="$(uuidgen)"
curl -X POST https://api.popnow.ai/api/v1/jobs/createTask \
  -H "Authorization: Bearer $POPNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $IDEMPOTENCY_KEY" \
  -d '{
  "model": "elevenlabs/dubbing/video-translate",
  "input": {
    "video_url": "https://media.popnow.ai/effects/flower-bloom-1abd6efb.mp4",
    "target_language": "en",
    "source_language": "auto"
  }
}'

# 2. Copy data.taskId from the response, then poll until state is succeeded, failed, canceled or expired.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
  -H "Authorization: Bearer $POPNOW_API_KEY"

Replace the prompt and any links with your own. The API tab has the response, polling and callback reference.

ElevenLabs Dubbing API questions

How much does the ElevenLabs Dubbing API cost?

ElevenLabs Dubbing starts at $0.012 per second with Video Translator, its lowest-priced task. API usage is charged in USD to your PopNow balance. When a task is accepted, we reserve the maximum quoted amount from your API balance. On completion, we charge for actual usage, never more than the hold, and release the remainder. If the task fails, the hold is released.

What is the model name for ElevenLabs Dubbing in the API?

Put elevenlabs/dubbing/video-translate for Video Translator; elevenlabs/dubbing/audio-to-audio for Audio Translator in the model field of POST /jobs/createTask.

How do I call the ElevenLabs Dubbing API?

Submit a task with model set to elevenlabs/dubbing/audio-to-audio or elevenlabs/dubbing/video-translate and the matching audio_url or video_url inside input. Choose target_language, then retrieve the completed task’s media asset. The endpoint guides below show request bodies and trimmed result examples.

Can I translate a podcast without supplying video?

A podcast recording can go directly to the audio-to-audio endpoint and return as a dubbed MP3. For an English-to-Spanish translation, use audio_url with target_language set to es. Keep each submitted recording within 15 minutes.

Does video dubbing also change lip movements?

Video dubbing here replaces the audio track and leaves the picture untouched. Our 6.04-second video test returned a video stream that was byte-identical to the source. For translation with lip movement, consider [HeyGen Video Translate](/models/heygen-video-translate).

Will speakers still sound like themselves?

ElevenLabs says dubbing retains the voice character of the original speakers in another language. Treat resemblance as something to review on your actual recording, rather than a guarantee of an unchanged accent or performance. Use recordings of yourself or people who agreed, use material you have rights to use, and never impersonate a real person.

How should I handle several people speaking?

Set speaker_count from 1 to 32 when you know how many distinct speakers the recording contains. Omit that field to let the service detect them. Review turn changes and overlapping dialogue in a short excerpt before dubbing the complete recording.

What are the limits of the ElevenLabs Dubbing API?

Longest input clip: 900 s. Requests outside these limits are rejected before anything is charged.

Can I try ElevenLabs Dubbing without writing code?

Run ElevenLabs Dubbing in the Playground with your API USD balance, without an API key. Each run appears in your developer history with its matching code.

All ElevenLabs models

HeyGen Video Translate redraws the lips to match the new speech, for clips up to 120 seconds. Choose ElevenLabs Dubbing for long recordings, audio-only sources, or when the lips don't need to move.

More about ElevenLabs Dubbing