Name: ElevenLabs Dubbing API: AI Audio and Video Dubbing
Brand: magicapi
SKU: api-magicapi-audio-video-translation-preserve-voice-emotion-timing-elevenlabs-dubbing
Availability: InStock
Author: API Market

Shashank Agarwal

# 🎙️ Audio and Video Dubbing API (ElevenLabs Dubbing)

## Overview
ElevenLabs Dubbing translates the speech in an audio or video file into another language. Its developer describes it as translating audio and video into 90+ languages while preserving each speaker's voice, emotion and timing.

Send a file (`audio_or_video_file`) or a public link (`source_url`) and a `target_language`. The model returns the URL of the dubbed file.

## Features
- **108 target languages and dialects**: BCP-47 tags such as `fr`, `de`, `hi`, `ja`, plus regional variants like `es-MX`, `pt-BR`, `en-GB` and `fr-CA`.
- **Automatic source language**: `source_language` defaults to `auto` and detects the spoken language; set it explicitly if you know it.
- **Voice cloning strength**: `cloning_strength` (0 to 10, default 7) balances resemblance to the original voices against natural delivery in the target language.
- **File or link input**: upload a file as `audio_or_video_file`, or pass `source_url` with a direct file link or a YouTube or TikTok URL.

## Use Cases
1. **Video localization**: publish tutorials, product videos and courses in several languages with the original speakers' voices.
2. **Podcasts and interviews**: release translated episodes that keep each host's voice.
3. **Social media clips**: dub short videos for audiences in other markets.
4. **Internal communications**: translate recorded announcements and training material for global teams.

## Visual Examples
### Example Input
Source audio: [Listen to the example input (English)](https://blog.api.market/wp-content/uploads/2026/10/dubbing-input-api-market.mp3)

Settings: `source_url` set to the file above, `source_language` `en`, `target_language` `fr`.

### Example Output
[Listen to the example output (French dub)](https://blog.api.market/wp-content/uploads/2026/10/dubbing-output-95vc1019-api-market.mp3)

The dubbed audio is 14.8 seconds long.

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `target_language` | string | Yes |  | `af`, `ak`, `sq`, `am`, `ar`, `ar-EG`, `hy`, `as`, `az`, `eu`, `be`, `bs`, `bg`, `my`, `yue`, `ca`, `ceb`, `zh`, `zh-TW`, `hr`, `cs`, `da`, `dgo`, `nl`, `en`, `en-AU`, `en-CA`, `en-GB`, `en-US`, `et`, `fil`, `fi`, `fr`, `fr-CA`, `fr-FR`, `gl`, `ka`, `de`, `el`, `gu`, `ha`, `he`, `hi`, `hu`, `is`, `id`, `it`, `ja`, `jv`, `kn`, `kk`, `ki`, `rw`, `rn`, `ko`, `ky`, `lv`, `lt`, `lg`, `mk`, `ms`, `ml`, `cmn`, `mr`, `mn`, `ne`, `no`, `fa`, `pl`, `pt`, `pt-BR`, `pt-PT`, `pa`, `ro`, `ru`, `nso`, `st`, `sd`, `sk`, `sl`, `es`, `es-AR`, `es-CL`, `es-ES`, `es-MX`, `su`, `sw`, `ss`, `sv`, `tg`, `ta`, `te`, `th`, `bo`, `ts`, `tn`, `tr`, `uk`, `ur`, `ug`, `uz`, `ve`, `vi`, `war`, `cy`, `wo`, `yo`, `zu` | Language to dub the content into, as a BCP-47 tag. Some languages also offer region-qualified dialects (for example `es-MX`, `pt-BR`, `en-GB`) |
| `audio_or_video_file` | string (URL) | No | none |  | Audio or video file to dub. Provide this or `source_url` |
| `source_url` | string | No | none |  | Public URL of the source audio or video file to dub (a direct link, or a YouTube or TikTok URL). Provide this or `audio_or_video_file` |
| `source_language` | string | No | `auto` | `auto` or any `target_language` value | Language of the source media, as a BCP-47 tag. Leave as `auto` to detect it automatically |
| `cloning_strength` | integer | No | `7` | 0 to 10 | How strongly the dubbed speakers clone the source voices. Higher values prioritize resemblance to the original voice; lower values give the model more freedom for natural delivery in the target language. The default of 7 works well for most content |

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.046 per API unit.
- **1 API unit = 1 second of dubbed output audio**, rounded up to a whole second per request. One minute of dubbed audio costs $2.76.
- The price is the same for every language pair and `cloning_strength`.
- The example request above produced 14.811 seconds of audio, billed as 15 units: $0.69.
- If a finished request does not report its output duration, it is billed as 60 units ($2.76).
- **Failed or cancelled predictions are not billed.**
- **GET requests to check prediction status** are free and don't count toward API unit usage.
- **No monthly subscription fee.**

## API Documentation

### Base URL
All API requests go to: `https://prod.api.market/api/v1/magicapi/audio-video-translation-preserve-voice-emotion-timing-elevenlabs-dubbing`

### Authentication
Send your api.market API key in the `x-api-market-key` header:
```
x-api-market-key: YOUR_API_MARKET_KEY
```

### Asynchronous Processing
**IMPORTANT**: This API is asynchronous. The flow is:
1. Send a POST request to `/predictions`. A successful request returns **201 Created** with a prediction `id` and a `status` of `starting` or `processing`.
2. Poll GET `/predictions/{id}` with that ID.
3. Keep polling while `status` is `starting` or `processing`.
4. Stop when `status` is `succeeded` (read `output`), `failed` or `canceled` (read `error`).

A polling interval of 2 seconds and an overall timeout of 600 seconds (10 minutes) work well. Long files take longer; raise the timeout for them.

### Endpoints

#### Create a Prediction
```bash
curl -X POST "https://prod.api.market/api/v1/magicapi/audio-video-translation-preserve-voice-emotion-timing-elevenlabs-dubbing/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "elevenlabs/dubbing",
    "input": {
      "source_url": "https://blog.api.market/wp-content/uploads/2026/10/dubbing-input-api-market.mp3",
      "source_language": "en",
      "target_language": "fr"
    }
  }'
```

Response (201 Created):
```json
{
  "id": "95vc1019y5rmy0d1ccn8hbvg5g",
  "version": "elevenlabs/dubbing",
  "status": "starting",
  "created_at": "2026-10-22T10:31:10.231Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/audio-video-translation-preserve-voice-emotion-timing-elevenlabs-dubbing/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "95vc1019y5rmy0d1ccn8hbvg5g",
  "status": "succeeded",
  "output": "https://blog.api.market/wp-content/uploads/2026/10/dubbing-output-95vc1019-api-market.mp3",
  "error": null,
  "created_at": "2026-10-22T10:31:10.231Z",
  "started_at": "2026-10-22T10:31:10.241Z",
  "completed_at": "2026-10-22T10:31:26.625Z"
}
```

`output` is a single URL string pointing to the dubbed file. The example's MP3 input returned an MP3.

### Status Codes
- **201 Created**: prediction created (POST `/predictions`). This is the normal success response.
- **200 OK**: prediction details returned (GET `/predictions/{id}`).
- **400 Bad Request**: invalid input, for example a missing `target_language` or a language code that is not in the list.
- **401 Unauthorized**: missing or invalid API key.
- **404 Not Found**: no prediction with that ID.
- **429 Too Many Requests**: rate limit exceeded.
- **500 Internal Server Error** or **503 Service Unavailable**: temporary server problem; retry later.

## Rate Limits
All plans allow 10 requests per second. Requests above that return `429 Too Many Requests`; back off before retrying and honour any `Retry-After` header. Polling a prediction with GET is free but still counts toward the per-second limit, so poll every 1 to 5 seconds rather than in a tight loop.

## Error Handling
- Check the HTTP status code of every request and read the response body for the error message.
- A prediction can also end with `status` set to `failed`; the `error` field then explains why. Failed predictions are not billed.
- Retry 429, 500 and 503 responses with exponential backoff. Fix the input before retrying a 400.

## Implementation Guide
### Example Code

#### JavaScript
```javascript
const apiKey = "YOUR_API_MARKET_KEY";
const baseUrl = "https://prod.api.market/api/v1/magicapi/audio-video-translation-preserve-voice-emotion-timing-elevenlabs-dubbing";

async function createAndWaitForPrediction(input) {
  const response = await fetch(`${baseUrl}/predictions`, {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      "x-api-market-key": apiKey
    },
    body: JSON.stringify({ version: "elevenlabs/dubbing", input })
  });

  if (response.status !== 201) {
    throw new Error(`API error: ${response.status} ${await response.text()}`);
  }

  const prediction = await response.json();
  return pollForResults(prediction.id);
}

const delay = (ms) => new Promise((resolve) => setTimeout(resolve, ms));

async function pollForResults(predictionId) {
  const maxTimeout = 600000;
  const pollInterval = 2000;
  const startTime = Date.now();

  while (Date.now() - startTime < maxTimeout) {
    const response = await fetch(`${baseUrl}/predictions/${predictionId}`, {
      headers: { "x-api-market-key": apiKey }
    });

    if (!response.ok) {
      throw new Error(`API error: ${response.status} ${await response.text()}`);
    }

    const prediction = await response.json();

    if (prediction.status === "succeeded") {
      return prediction.output;
    }

    if (prediction.status === "failed" || prediction.status === "canceled") {
      throw new Error(`Prediction ${prediction.status}: ${prediction.error || "Unknown error"}`);
    }

    await delay(pollInterval);
  }

  throw new Error("Prediction timed out after 10 minutes");
}

createAndWaitForPrediction({
  source_url: "https://blog.api.market/wp-content/uploads/2026/10/dubbing-input-api-market.mp3",
  source_language: "en",
  target_language: "fr"
}).then((output) => console.log(output));
```

#### Python
```python
import time
import requests

API_KEY = "YOUR_API_MARKET_KEY"
BASE_URL = "https://prod.api.market/api/v1/magicapi/audio-video-translation-preserve-voice-emotion-timing-elevenlabs-dubbing"


def create_and_wait_for_prediction(input_data):
    headers = {"Content-Type": "application/json", "x-api-market-key": API_KEY}
    response = requests.post(
        f"{BASE_URL}/predictions",
        headers=headers,
        json={"version": "elevenlabs/dubbing", "input": input_data},
    )

    if response.status_code != 201:
        raise Exception(f"API error: {response.status_code} {response.text}")

    return poll_for_results(response.json()["id"])


def poll_for_results(prediction_id):
    max_timeout = 600
    poll_interval = 2
    headers = {"x-api-market-key": API_KEY}
    start_time = time.time()

    while time.time() - start_time < max_timeout:
        response = requests.get(f"{BASE_URL}/predictions/{prediction_id}", headers=headers)

        if response.status_code != 200:
            raise Exception(f"API error: {response.status_code} {response.text}")

        prediction = response.json()

        if prediction["status"] == "succeeded":
            return prediction["output"]

        if prediction["status"] in ("failed", "canceled"):
            raise Exception(f"Prediction {prediction['status']}: {prediction.get('error') or 'Unknown error'}")

        time.sleep(poll_interval)

    raise Exception("Prediction timed out after 10 minutes")


print(create_and_wait_for_prediction({
    "source_url": "https://blog.api.market/wp-content/uploads/2026/10/dubbing-input-api-market.mp3",
    "source_language": "en",
    "target_language": "fr",
}))
```

## FAQ
- **Do I send a file or a link?**
  - Either. Upload the media as `audio_or_video_file`, or pass a public `source_url` (a direct file link, or a YouTube or TikTok URL). Send one of the two.
- **Do I need to set the source language?**
  - No. `source_language` defaults to `auto` and detects it. Setting it, as in the example (`en`), avoids a wrong guess on short or mixed-language clips.
- **The dub does not sound enough like the original speaker. What can I change?**
  - Raise `cloning_strength` toward 10 for closer resemblance. Lower it for more natural delivery in the target language.
- **How much does dubbing cost?**
  - $0.046 per second of dubbed audio, rounded up per request, so $2.76 per minute. The 14.8-second example cost $0.69.
- **Is the 201 response from POST an error?**
  - No. 201 Created means the prediction was accepted. Use the returned `id` to poll GET `/predictions/{id}` until `status` is `succeeded`, `failed` or `canceled`.
- **What if my prediction fails?**
  - Failed predictions are not billed. Read the `error` field, adjust the input and try again.

## Contact Us
If you have any questions, reach out to us through the chat on the bottom right of the page. You can also email our support team at hello@magicapi.com.


Translate and dub audio or video files into 108 languages and dialects with ElevenLabs Dubbing, keeping the original voices. $2.76 per call of dubbed audio.