translate
API

AI Dubbing API

Upload audio, choose a target language, and receive dubbed output through one async task.

What is AI Dubbing API?

Dubbing is built as a task-based localization flow. Submit source audio, choose the target language, and retrieve dubbed audio plus optional subtitle artifacts once the task finishes.

Supported Models

Voice-preserving dubbing

Task-based multilingual dubbing with optional subtitle artifacts

Speaker-aware flow

Control speaker detection and voice cloning behavior through request fields

Quick Start

Python
api.cheapaiapi.com
import requests

# Submit dubbing task
with open("video.mp4", "rb") as f:
    resp = requests.post(
        "https://api.cheapaiapi.com/v1/task/dubbing",
        headers={"Authorization": "Bearer sk-your-key"},
        files={"file": f},
        data={
            "target_lang": "Spanish",
            "source_lang": "auto"
        }
    )
task_id = resp.json()["task_id"]

# Poll for completion
import time
while True:
    status = requests.get(
        f"https://api.cheapaiapi.com/v1/task/{task_id}",
        headers={"Authorization": "Bearer sk-your-key"}
    ).json()
    if status["status"] == "done":
        print(status["metadata"]["audio_url"])
        break
    time.sleep(5)

Why CheapAI?

voice_over_off

Voice Preservation

Keep the original speaker feel while moving the content into another language.

language

Target Language Flow

Choose the output language in the create request and track the job asynchronously.

subtitles

Artifact Output

Finished tasks can return dubbed audio plus transcript-style files.

Async

Flow

Yes

Voice Preservation

Multipart Upload

Input

Task Based

Delivery

Frequently Asked Questions

How does voice preservation work?expand_more

The dubbing workflow aims to preserve the original speaker feel while rendering the content in the target language.

How do I retrieve the final result?expand_more

Poll the common task endpoint and read the dubbed audio and subtitle URLs from the completed task metadata.

Can I control speakers?expand_more

Yes. The request supports speaker-related fields such as speaker count and voice cloning behavior.

Start Building Today

Get $2 in free credits. Create an API key, set spend controls if needed, and start testing the current task-based endpoints.

Get API Key arrow_forward