Introduction
Supply video_url for a recording up to 15 minutes and choose the language for its spoken track. The endpoint returns MP4 video with replaced audio while leaving the filmed image and lip movements unchanged. Subtitles are not included.
| Field | Value |
|---|---|
| Input | Video |
| Output | Video |
| Publisher and product | ElevenLabs — ElevenLabs Dubbing |
| Release date | October 10, 2023 |
| Public audio API name | elevenlabs/dubbing/audio-to-audio |
| Public video API name | elevenlabs/dubbing/video-translate |
| Source duration limit | 15 minutes; longer sources rejected at submission |
| Target languages | 33; |
| Source languages | 57 plus auto detection |
| Speaker count | 1–32; omit |
| Background sound |
|
| Audio output observed | MP3; 4.50 s, 44.1 kHz mono, 128 kbps in our audio test |
| Video output observed | MP4; 6.04 s with new mono AAC audio and byte-identical video stream in our test |
| Billing unit | Seconds of source media, rounded up |
Key features & highlights
An MP3 dub or a translated MP4
Audio-to-audio accepts a recording and returns dubbed MP3 audio. Video-translate returns an MP4 with the picture preserved and its audio track replaced. Both accept sources up to 15 minutes, so choose the endpoint according to the media you need back.
33 targets, with speaker detection
Choose from 33 target languages and 57 source languages, or let source detection run automatically. Set speaker_count between 1 and 32 when the cast is known; omit it for detection. ElevenLabs says its dubbing carries each speaker’s voice character into the translated speech.
Retain the recording’s background
Enable keep_background_audio when music or ambience belongs in the translated recording. Review the balance with the new voices before using the result. For video, this soundtrack decision does not alter the filmed image or produce subtitles.
9.6 seconds for our audio sample
Our 4.5-second English-to-Spanish audio test returned a 4.50-second MP3 after about 9.6 seconds of processing. The file was 44.1 kHz mono at 128 kbps. A separate 6.04-second video took about 14.8 seconds and returned MP4 with a new mono AAC track; these are sample observations.
Request parameters
| Parameter | Required | Description |
|---|---|---|
video_url | Yes | Supply the video whose spoken soundtrack you want to translate, up to 15 minutes long. at least 1 characters |
target_language | No | Choose one of 33 destination languages for the dubbed soundtrack; the default is en. Use es for an English-to-Spanish review clip. |
source_language | No | Use auto to detect the spoken language or specify one of 57 source languages. Select the known source when you want an explicit language setting for a trial dub. |
speaker_count | No | Enter the number of distinct people speaking, from 1 through 32, or leave it out for automatic detection. Check the translated soundtrack at each speaker change. |
keep_background_audio | No | Turn this on when the video’s music and ambience should remain beneath the new dialogue. This setting concerns sound and does not change the picture or lip movement. Default: |
Pricing
$0.012 / second
The source clip is billed by the second with fractional seconds rounded upward; accepted sources run up to 15 minutes. Language and speaker settings leave the rate unchanged, and a failed task is not charged.
Use cases
A podcast interview in Spanish
Submit a 12-minute English interview through audio_url, choose es, and set speaker_count to 2 for its host and guest. The audio endpoint returns a translated MP3 for review and inclusion in a Spanish edition.
A spoken customer update in English
Provide a 45-second voice note recorded by a colleague who agreed to translation, with en as the target. Receive dubbed MP3 speech that you can review before sharing the update.
A narrated lesson with its visuals
Send a 6-minute screen-recorded lesson through video_url and select the intended target language. The returned MP4 keeps the screen demonstration while replacing the spoken track; create captions separately if needed.
An audio advertisement with music
Use a 30-second recorded advertisement you have rights to use and enable keep_background_audio. The output is an MP3 with translated voices and the retained music or ambience beneath them.
A product demonstration for another market
Supply a 90-second product walkthrough as video input and choose a supported target language. Receive an MP4 with the same picture and a dubbed soundtrack, suitable for a language review before release.
Prompt guide & pro tips
Prepare a permitted recording
Choose an audio or video source no longer than 15 minutes, using your own recording or speakers who agreed to dubbing. Confirm that you have the rights to the speech and any music.
Choose languages and speakers
Select one of 33 target languages and use automatic detection or one of 57 source languages. Enter
speaker_countfrom 1 to 32 when known, and decide whether to retain the background soundtrack.Submit the dubbing request
POST https://api.spicyapi.ai/api/v1/jobs/createTask with Bearer authentication and JSON such as {"model":"elevenlabs/dubbing/audio-to-audio","input":{"
audio_url":"https://example.com/narration.mp3","target_language":"es"}}. For video, select elevenlabs/dubbing/video-translate and supplyvideo_urlinstead.Retrieve and review the media
Read the task with GET /api/v1/jobs/recordInfo?taskId= until its state is succeeded, then download the returned asset. Check the translated speech and speaker changes; a video dub keeps the filmed lip movements.
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. Submit this JSON with POST to https://api.spicyapi.ai/api/v1/jobs/createTask, adding Authorization: Bearer <SPICY_API_KEY> and Content-Type: application/json headers.
{
"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.
| Field | Supported setting | Effect on this request |
|---|---|---|
video_url | Video source up to 15 minutes | Supplies the picture and spoken soundtrack |
target_language | 33 target choices; en by default | Determines the translated speech language |
source_language | 57 source choices or auto | Specifies the speech language or requests detection |
speaker_count | Integer 1–32, or omitted | Supplies a known cast size or requests detection |
keep_background_audio | Retain music and ambience | Keeps 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.
| Workflow | Input and output | Reason to choose it |
|---|---|---|
| ElevenLabs Dubbing audio-to-audio | Audio to dubbed MP3 | A podcast, narration, or voice note |
| ElevenLabs Dubbing video-translate | Video to dubbed MP4 | Translated speech with the picture retained |
| HeyGen Video Translate | Video translation with lip movement | A delivery that needs lip movement |
| Video Translator V1 | Video translation | Another option for a video source |
These alternatives were not measured in our ElevenLabs tests.
Video dubbing charges
The billing unit is a second of source video, with fractional seconds rounded upward. Check the rate displayed on this page and the source clip’s duration when estimating the task.
A preview helps you assess a language and its speaker transitions before sending an entire lesson. Its processing time does not predict the wait for a longer source.
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.
- Confirm rights to the footage, its speech, and any music, with agreement from the recorded speakers.
- Choose a representative excerpt with the speaker changes or terminology you need to assess.
- Specify the target language and a known source language, or use source detection.
- Set the cast count when known and decide whether the existing ambience belongs in the dub.
- 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.
API quick start
# Generate the idempotency key once; reuse it when retrying after a lost response.
export SPICY_IDEMPOTENCY_KEY="${SPICY_IDEMPOTENCY_KEY:-$(uuidgen)}"
curl -X POST https://api.spicyapi.ai/api/v1/jobs/createTask \
-H "Authorization: Bearer $SPICY_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $SPICY_IDEMPOTENCY_KEY" \
-d '{
"model": "elevenlabs/dubbing/video-translate",
"input": {
"source_language": "auto",
"target_language": "en",
"video_url": "https://example.com/reference.mp4"
}
}'
# Copy data.taskId from the response into TASK_ID, then poll the status.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.spicyapi.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
-H "Authorization: Bearer $SPICY_API_KEY"
See the API reference for authentication, the complete schema, polling, and error handling.




