API Docs
API Docs
Video Translation – Voice Cloning
Translate spoken content in videos into other languages while preserving the original speaker’s voice using AI-powered voice cloning.
Create Video Translation with Voice Cloning Request
/api/vt-w-vc
This endpoint translates spoken content in a video from one language to another while cloning the original speaker’s voice. The pipeline includes speech recognition, translation, and voice-cloned speech synthesis to generate a translated video output.
Requests are processed asynchronously. Once accepted, the API returns a unique log_id that can be used to track processing status and retrieve the final translated video.
Request Body
project_title (string, required)
A human-readable title to identify the video translation project.
Example: "My Project"
file (file, optional)
Video file to be translated. Required if youtube_url is not provided.
Example: "video.mp4"
youtube_url (string, optional)
YouTube video URL to translate. Required if file is not provided. Do not provide both file and youtube_url.
Example: "https://www.youtube.com/watch?v=XXXX"
output_language (string, required)
Target language into which the video should be translated.
View example →avatar (string, required)
Voice avatar used for cloning the original speaker’s voice.
Example: "daaji"
ttt_model (string, required)
Text Translation model used to translate the recognized speech.
View example →stt_model (string, required)
Speech to Text model used to extract spoken content from the video.
Example: "narris_fast"
speed (number, optional)
Playback speed of the translated, voice-cloned audio. Defaults to 1.
Example: 1
pitch (number, optional)
Pitch adjustment for the cloned voice output. Defaults to 0.
0Note: You must provide either a video file or a youtube_url. Providing both or neither will result in a validation error.
Response
On successful submission, the API returns a unique log_id.
Use this log_id with the Fetch Video Translation Voice Cloning By ID endpoint to retrieve the translated video and processing metadata.
{
"log_id": "694d96ef7d5247d58c02984c"
}curl
curl --location 'https://api.narris.io/api/vt-w-vc' \ --header 'x-api-key: YOUR_API_KEY' \ --form 'project_title="My Project"' \ --form 'file=@"/path/to/video.mp4"' \ --form 'input_language="english"' \ --form 'output_language="hindi"' \ --form 'avatar="daaji"' \ --form 'ttt_model="narris"' \ --form 'stt_model="narris_fast"' \ --form 'speed="1"' \ --form 'pitch="0"'
Fetch Video Translation with Voice Cloning List
/api/vt-w-vc/logs
This endpoint allows you to fetch a paginated list of previously created video translation requests that use voice cloning.
Each entry represents a video translation job with voice cloning and includes its current status, input video reference, and timestamps.
Request Body
page (number, optional)
Page number for pagination.
Example: 1
limit (number, optional)
Number of records to return per page.
Example: 10
Response
On success, the API returns a paginated list of video translation with voice cloning logs.
Each log contains a unique _id which can be used with the Fetch Video Translation with Voice Cloning By ID endpoint to retrieve detailed output and metadata.
{
"total": 1,
"page": 1,
"limit": 10,
"logs": [
{
"_id": "694ae800734f6600f2cfa64a",
"project_title": "My Project",
"input_file": "https://lingui-dev.s3.amazonaws.com/input/trim_copy_1766516735897.mp4",
"status": "failed",
"createdAt": "2025-12-23T19:05:36.359Z",
"finishedAt": "2025-12-23T19:06:06.504Z"
}
]
}curl
curl --location 'https://api.narris.io/api/vt-w-vc/logs?page=1&limit=10' \ --header 'Content-Type: application/json' \ --header 'x-api-key: YOUR_API_KEY'
Fetch Video Translation with Voice Cloning By ID
/api/vt-w-vc/{log_id}
This endpoint allows you to fetch the complete details of a video translation with voice cloning request using its unique log_id.
The response includes input video details, source and target languages, speech recognition and translation models used, voice cloning configuration, processing status, timestamps, and the final translated video output if available.
Request Body
log_id (string, required)
Unique identifier of the video translation with voice cloning request returned during creation or from logs.
Example: "694ae800734f6600f2cfa64a"
Response
On success, the API returns detailed information about the video translation with voice cloning request.
If processing is completed successfully, the output_file field will contain the translated video URL.
If the request fails, the status field will be failed and no output file will be returned.
{
"_id": "694ae800734f6600f2cfa64a",
"project_title": "My Project",
"input_file": "https://lingui-dev.s3.amazonaws.com/input/trim_copy_1766516735897.mp4",
"input_language": "english",
"output_language": "hindi",
"avatar": "daaji",
"speed": "1",
"pitch": "0",
"ttt_model": "narris",
"stt_model": "narris_fast",
"status": "failed",
"createdAt": "2025-12-23T19:05:36.359Z",
"updatedAt": "2025-12-23T19:06:06.504Z",
"finishedAt": "2025-12-23T19:06:06.504Z"
}curl
curl --location 'https://api.narris.io/api/vt-w-vc/694ae800734f6600f2cfa64a' \ --header 'Content-Type: application/json' \ --header 'x-api-key: YOUR_API_KEY'
Notes for Developers
• Video Translation with Voice Cloning requests are processed asynchronously. Always store the returned log_id to track progress.
• Voice cloning preserves speaker characteristics such as tone, pitch, and speaking style while translating spoken content.
• Processing time may be longer than standard video translation due to speech synthesis and voice cloning steps.
• Use the Fetch Video Translation Voice Cloning List endpoint to view all jobs and Fetch Video Translation Voice Cloning By ID to retrieve the final dubbed video output.