> This is a page from the ElevenLabs documentation. For a complete page index, fetch https://elevenlabs.io/docs/llms.txt. For the full documentation in a single file, fetch https://elevenlabs.io/docs/llms-full.txt.

# Dubbing

## General

With our Productions dubbing offering, localize your content to reach any audience in the world. Share your video, source language, and destination language, and receive a fully dubbed video which is natural-sounding and production-ready.

* For more information about other Productions services, please see the [Overview](/docs/eleven-creative/services/productions/overview) page.

## How it works

#### Order a dub

The easiest way to order a dub from Productions is through the [Productions](https://elevenlabs.io/app/productions) page in your ElevenLabs account. Simply share:

* **Your video file** (MP4, MOV, AVI, MKV)
* **Source language** (e.g., English)
* **Target language** (e.g., Spanish, Hindi, Arabic)

![Productions Home](/docs/_fern-img/cd072dfc01c9b277960c0583a3900ca963ee0ca766f204f5fac602117f5a8174.webp)

#### Processing

Using proprietary AI models with human-in-the-loop craftsmanship, we:

* Accurately **transcribe** the source audio
* **Translate** into the requested target language with contextual accuracy
* **Generate** synthetic voices matched to speaker identity and tone, or use custom voices
* **Synchronize** dubbed speech with the original video timing

#### Order delivery

You'll receive a fully dubbed video with multiple export options: MP4 Video (default), AAC Audio, MP3 Audio, WAV Audio, Audio Tracks or Clips (Zip File), AAF (Timeline Data), SRT Captions, TXT Transcript.

**To export your completed dub:**

1. Access your order in the [Productions](https://elevenlabs.io/app/productions) page
2. Click **View** to open the project
3. Once inside the project, select your desired format from the export options
4. Choose whether to normalize the audio (optional)
5. Click **Export** to generate the file
6. You can then view or download your exported dub

## Behind the scenes

We follow a strict workflow to deliver consistent, natural-sounding dubs:

* **Transcription**: highly accurate transcription and speaker allocation.
* **Translation**: thorough review of translation accuracy by a native speaker, and edits to make the voice-over sound as natural as possible.
* **Voice selection**: we carefully pick the right voice for your dub, or use the voices you've shared with us.
* **Pacing**: we regenerate segments or edit the transcription to ensure the best possible pacing on each segment.
* **Quality control**: each dub goes through a checklist to ensure accuracy, consistency, and natural delivery.

## Pricing

Our dubbing prices depend on several factors, including languages, type of content, and services included. [Talk to sales](https://elevenlabs.io/contact-sales) to discuss your specific needs and get a custom quote.

## SLAs / Delivery time

We aim to deliver all dubbing projects **within 7 business days.** If you are an enterprise interested in achieving quicker turnaround times, please contact us at [productions@elevenlabs.io](mailto:productions@elevenlabs.io).

## FAQ

<tbody>
  <tr>
    <td>
      #### What video formats do you support?

      We support MP4, MOV, AVI, and MKV formats for video uploads. The final dubbed video is
      delivered in MP4 format by default.
    </td>
  </tr>

  <tr>
    <td>
      #### What if I'm not happy with the result?

      You can leave feedback on a completed dub by clicking the three dots (⋯) next to your
      deliverable and selecting *Feedback*.
    </td>
  </tr>

  <tr>
    <td>
      #### Can I make changes once I receive the final version?

      Yes, you can open the project in Dubbing Studio and make changes to refine the output.
    </td>
  </tr>

  <tr>
    <td>
      #### Do you provide lip sync?

      We do our best to match timing and visible mouth movements, but perfect lip sync is not
      guaranteed and may vary depending on the content.
    </td>
  </tr>
</tbody>

> ElevenLabs provides APIs and SDKs for text to speech, voice cloning, speech to text, sound effects, voice isolator, voice changer, and conversational AI agents. Build voice-enabled applications with lifelike audio generation.