elevenlabs/dubbing
Dubbing by ElevenLabs - advanced AI model for audio-to-video. Delivers high-quality results with fast inference, suitable for both creative and production workflows.
Example output — click Run to generate your own
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
https://api.sandbase.ai/v1/runelevenlabs/dubbingInput Schema
6 parameters · 0 required · 6 optional
| Parameter | Type | Required | Description |
|---|---|---|---|
audio | string | Optional | URL of the audio file to dub. Either audio_url or video_url must be provided. |
video | string | Optional | URL of the video file to dub. Either audio_url or video_url must be provided. If both are provided, video_url takes priority. |
source_lang | string | Optional | Source language code. If not provided, will be auto-detected. |
target_lang | string | Optional | Target language code for dubbing (ISO 639-1) |
num_speakers | integer | Optional | Number of speakers in the audio. If not provided, will be auto-detected. · Min: 1 · Max: 50 |
highest_resolution | boolean | Optional | Whether to use the highest resolution for dubbing. · Default: true |
Output Schema
| Field | Type | Description |
|---|---|---|
id | string | Unique identifier for the generation task |
status | string | Task status: pending, running, completed, failed, timeout |
model | string | Model used for the generation |
outputs | array | Array of output items |
outputs[].url | string | URL of the generated artifact |
outputs[].content_type | string | MIME type (e.g. image/png, video/mp4) |
error | object | null | Error details if failed, null on success |
error.type | string | Machine-readable error type code |
error.message | string | Human-readable error description |
Async Workflow
This model uses asynchronous execution. Submit a request and poll for the result.
- Submit — POST to /v1/run, receive an
id - Poll — GET /v1/run/{id} until status is
completed,failed, ortimeout - Retrieve — Read
outputsfrom the completed response
Code Examples
Ready-to-run snippets
# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "elevenlabs/dubbing",
"video": "https://static.sandbase.ai/examples/elevenlabs/dubbing/input_video_0.mp4",
"source_lang": "en",
"target_lang": "es",
"highest_resolution": true,
"prompt": "a beautiful sunset over mountains"
}'
# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
-H "Authorization: Bearer YOUR_API_KEY"API README
ElevenLabs Dubbing
ElevenLabs Dubbing localizes existing audio or video into another language while preserving the performance qualities that make each speaker recognizable. The dubbing workflow carries tone, pacing, delivery, and emotional intent across languages instead of producing a flat reading of a translated transcript.
It is designed for podcasts, interviews, creator videos, training material, and campaigns that need to reach new audiences without re-recording every participant. Multiple speakers can be handled within one source, while background music, effects, and ambience remain part of the localized result.
Highlights
- Performance-preserving translation. Carries speaker tone, pacing, delivery, and emotion into the target-language performance.
- Multiple-speaker handling. Separates and preserves distinct voices across conversations and overlapping dialogue.
- Background-audio retention. Keeps music, ambience, and effects so the localized track does not require a full remix.
- Audio and video input. Accepts existing media for localization rather than requiring a text-only narration workflow.
Pricing
| Configuration | Billing unit | Price |
|---|---|---|
| Source duration | Per second | $0.015 |
When to Use
| ✅ Good fit | ❌ Consider alternatives |
|---|---|
| The project needs localizing existing spoken media | The goal is a different media task or endpoint |
| The available inputs match the required local schema | Required source media or permissions are unavailable |
| The brief can specify subject, composition, style, and delivery | The result must be deterministic at pixel or sample level |
| The supported formats and controls match final placement | Delivery requires unsupported dimensions, codecs, or duration |
| An asynchronous generated result fits the workflow | A live, frame-synchronous, or real-time response is mandatory |
Prompt Guide
Write the request as a production brief: identify the main subject or source material, state the intended transformation, describe composition or timing, and finish with style, atmosphere, and delivery constraints. Keep preservation requirements separate from requested changes, and use only fields exposed by this route.
{
"audio": "https://example.com/reference.mp3",
"video": "https://example.com/source.mp4",
"source_lang": "example"
}
Technical Specs
| Spec | Value |
|---|---|
| Model ID | elevenlabs/dubbing |
| Input fields | audio (string)<br>video (string)<br>source_lang (string)<br>target_lang (string)<br>num_speakers (integer; 1–50)<br>highest_resolution (boolean) |
| Required input | None marked required |
| Output fields | url, content_type |
| Execution | Asynchronous job |
Related Models
elevenlabs/sound-effects-v2