curl -X POST 'https://api.elevenlabs.io/v1/dubbing' \
  -H "xi-api-key: $ELEVENLABS_API_KEY" \
  -F 'file=@sample.bin' \
  -F 'csv_file=@sample.bin' \
  -F 'foreground_audio_file=@sample.bin' \
  -F 'background_audio_file=@sample.bin' \
  -F 'name=string' \
  -F 'source_url=string' \
  -F 'source_lang=auto' \
  -F 'target_lang=string' \
  -F 'target_accent=string' \
  -F 'num_speakers=0' \
  -F 'watermark=false' \
  -F 'start_time=0' \
  -F 'end_time=0' \
  -F 'highest_resolution=false' \
  -F 'drop_background_audio=false' \
  -F 'use_profanity_filter=true' \
  -F 'dubbing_studio=false' \
  -F 'disable_voice_cloning=false' \
  -F 'mode=automatic' \
  -F 'csv_fps=0'

# POST /v1/dubbing (ElevenLabs API)
Base URL: https://api.elevenlabs.io
Auth: xi-api-key: <ELEVENLABS_API_KEY>
Last verified: 2026-09-03

> Dub A Video Or An Audio File

## Critical Gotchas
* Authentication uses the non-standard `xi-api-key` header, not `Authorization: Bearer`. Sending a Bearer token returns HTTP 401.
* Text-to-speech responses are raw binary audio, not JSON. Write the body to a file (`--output speech.mp3`) rather than parsing it.

## cURL
curl -X POST 'https://api.elevenlabs.io/v1/dubbing' \
  -H "xi-api-key: $ELEVENLABS_API_KEY" \
  -F 'file=@sample.bin' \
  -F 'csv_file=@sample.bin'

## Parameters
| Name | In | Type | Required | Description |
| :--- | :--- | :--- | :--- | :--- |
| file | body | string | No | A list of file paths to audio recordi... |
| csv_file | body | string | No | CSV file containing transcription/tra... |
| foreground_audio_file | body | string | No | For use only with csv input |

## Response (200 OK)
{"dubbing_id":"21m00Tcm4TlvDq8ikWAM","expected_duration_sec":127.5}

---
Need an API key? Get one at https://elevenlabs.io/app/sign-up

POST

/v1/dubbing

ElevenLabs API

Dub A Video Or An Audio File

Base URL: https://api.elevenlabs.io
Auth: xi-api-key: <ELEVENLABS_API_KEY>
Last verified: 2026-09-03 · upstream hash matched

Actions

Agents: curl -H "Accept: text/markdown" this URL
→ 215 tokens · Vary: Accept

Critical gotchas

Authentication uses the non-standard xi-api-key header, not Authorization: Bearer. Sending a Bearer token returns HTTP 401.

Text-to-speech responses are raw binary audio, not JSON. Write the body to a file (--output speech.mp3) rather than parsing it.

cURL

curl -X POST 'https://api.elevenlabs.io/v1/dubbing' \  -H "xi-api-key: $ELEVENLABS_API_KEY" \  -F 'file=@sample.bin' \  -F 'csv_file=@sample.bin' \  -F 'foreground_audio_file=@sample.bin' \  -F 'background_audio_file=@sample.bin' \  -F 'name=string' \  -F 'source_url=string' \  -F 'source_lang=auto' \  -F 'target_lang=string' \  -F 'target_accent=string' \  -F 'num_speakers=0' \  -F 'watermark=false' \  -F 'start_time=0' \  -F 'end_time=0' \  -F 'highest_resolution=false' \  -F 'drop_background_audio=false' \  -F 'use_profanity_filter=true' \  -F 'dubbing_studio=false' \  -F 'disable_voice_cloning=false' \  -F 'mode=automatic' \  -F 'csv_fps=0'

Get a free ElevenLabs API key → sponsored

Parameters

Name	In	Type	Required	Description
file	body	string	No	A list of file paths to audio recordings intended for voice cloning
csv_file	body	string	No	CSV file containing transcription/translation metadata
foreground_audio_file	body	string	No	For use only with csv input
background_audio_file	body	string	No	For use only with csv input
name	body	string	No	Name of the dubbing project.
source_url	body	string	No	URL of the source video/audio file.
source_lang	body	string	No	Source language. Expects a valid iso639-1 or iso639-3 language code.
target_lang	body	string	No	The Target language to dub the content into. Expects a valid iso639-1 or iso639-3 language code.
target_accent	body	string	No	[Experimental] An accent to apply when selecting voices from the library and to use to inform translation of the dialect to prefer.
num_speakers	body	integer	No	Number of speakers to use for the dubbing. Set to 0 to automatically detect the number of speakers
watermark	body	boolean	No	Whether to apply watermark to the output video.
start_time	body	integer	No	Start time of the source video/audio file.
end_time	body	integer	No	End time of the source video/audio file.
highest_resolution	body	boolean	No	Whether to use the highest resolution available.
drop_background_audio	body	boolean	No	An advanced setting. Whether to drop background audio from the final dub. This can improve dub quality where it's known that audio shouldn't have a background track such as for speeches or monologues.
use_profanity_filter	body	boolean	No	[BETA] Whether transcripts should have profanities censored with the words '[censored]'
dubbing_studio	body	boolean	No	Whether to prepare dub for edits in dubbing studio or edits as a dubbing resource.
disable_voice_cloning	body	boolean	No	Instead of using a voice clone in dubbing, use a similar voice from the ElevenLabs Voice Library. Voices used from the library will contribute towards a workspace's custom voices limit, and if there aren't enough available slots the dub will fail. Using this feature requires the caller to have the 'add_voice_from_voice_library' permission on their workspace to access new voices.
mode	body	string	No	The mode in which to run this Dubbing job. Defaults to automatic, use manual if specifically providing a CSV transcript to use. Note that manual mode is experimental and production use is strongly discouraged.
csv_fps	body	number	No	Frames per second to use when parsing a CSV file for dubbing. If not provided, FPS will be inferred from timecodes.

Response 200 OK

{
  "dubbing_id": "21m00Tcm4TlvDq8ikWAM",
  "expected_duration_sec": 127.5
}