Dubbing

Dubbing is supported natively on POST /v2/generate. Pass the dubParams object alongside your normal generation request and Sync Labs will extract audio from the video input, dub it into the target language, and run lipsync on the dubbed result — all as one job.

When to use dubbing

• Native dubParams flow (this page): single API call, recommended for standard translation-plus-lipsync workflows.
• Manual orchestration: when you need custom control over transcription, TTS voice cloning, or intermediate steps, see the Translation/Dubbing tutorial which wires ElevenLabs, OpenAI, and Sync Labs together manually.

Workflow

DubDto fields

See the full API reference for dubParams.

• providerName (DubProviderName, required): dubbing provider to use. Currently elevenlabs is the only supported value.
• targetLang (DubLanguage, required): target language code for dubbing, e.g. es, fr, ja.
• sourceLang (DubSourceLanguage, optional, default auto): source language code, or auto to let the engine detect it.
• numSpeakers (integer, optional, default 0): number of speakers in the source video. 0 enables auto-detection; otherwise set a value between 1 and 50.

Request examples

1
import { SyncClient } from "@sync.so/sdk";
2
3
const sync = new SyncClient();
4
5
const response = await sync.generations.create({
6
  model: "lipsync-2",
7
  input: [
8
    { type: "video", url: "https://assets.sync.so/docs/example-video.mp4" }
9
  ],
10
  dubParams: {
11
    providerName: "elevenlabs",
12
    targetLang: "es"
13
  }
14
});

1
from syncsdk import Sync
2
3
client = Sync()
4
5
response = client.generations.create(
6
    model="lipsync-2",
7
    input=[
8
        {"type": "video", "url": "https://assets.sync.so/docs/example-video.mp4"}
9
    ],
10
    dub_params={
11
        "provider_name": "elevenlabs",
12
        "target_lang": "es"
13
    },
14
)

$
curl -X POST https://api.sync.so/v2/generate \
>
  -H "x-api-key: $SYNC_API_KEY" \
>
  -H "Content-Type: application/json" \
>
  -d '{
>
    "model": "lipsync-2",
>
    "input": [
>
      { "type": "video", "url": "https://assets.sync.so/docs/example-video.mp4" }
>
    ],
>
    "dubParams": {
>
      "providerName": "elevenlabs",
>
      "targetLang": "es"
>
    }
>
  }'

Behavior notes

• When dubParams is provided, audio is extracted from the video input, dubbed via ElevenLabs into the target language, and lipsync is run against the dubbed audio.
• Any audio inputs in the input array are ignored when dubbing is enabled — pass only the video input.
• A probed audio duration is required on the source video; dubbing requests without a decodable audio track are rejected.
• Billing is reported per dubbed output minute. See the Billing page for details.

See also

• Models → Lipsync — underlying lipsync model used after dubbing.
• Translation/Dubbing tutorial — legacy multi-service orchestration with fine-grained control.