API Docs
API Docs
Text to Speech – Voice Cloning
Generate speech using cloned voices by combining text input with reference voice samples.
Create Text to Speech Voice Cloning Request
/api/tts-w-vc
This endpoint converts written text into speech using a cloned human voice. The voice is selected using a predefined avatar profile.
The request is processed asynchronously. Once accepted, the API returns a unique log_id which can be used to track synthesis progress and retrieve the generated audio.
Request Body
project_title (string, required)
A human-readable title to identify the voice cloning project.
Example: "My Project"
input_text (string, required)
The text content that will be synthesized using the cloned voice.
Example: "Hello world"
language (string, required)
Language of the input text used for speech synthesis (for example: english, hindi).
View example →avatar (string, required)
Identifier of the cloned voice avatar to be used for speech synthesis.
Example: "daaji"
Response
On successful submission, the API returns a unique log_id.
Use this log_id with the Fetch Text to Speech Voice Cloning By ID endpoint to retrieve the generated audio and processing details.
{
"log_id": "695031477d5247d58c029e85"
}curl
curl --location 'https://api.narris.io/api/tts-w-vc' \
--header 'Content-Type: application/json' \
--header 'x-api-key: YOUR_API_KEY' \
--data '{
"project_title": "My Project",
"input_text": "Hello world",
"language": "english",
"avatar": "daaji"
}'Fetch Text to Speech Voice Cloning List
/api/tts-w-vc/logs
This endpoint allows you to fetch a paginated list of text to speech requests generated using cloned voice avatars.
Each entry represents a voice cloning job and includes its current status, synthesis parameters, creation time, and completion time (if available).
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 voice cloning logs.
Each log contains a unique _id which can be used with the Fetch Text to Speech Voice Cloning By ID endpoint to retrieve detailed synthesis results and generated audio.
{
"total": 10,
"page": 1,
"limit": 10,
"logs": [
{
"_id": "695031477d5247d58c029e85",
"project_title": "My Project",
"speed": "1",
"pitch": "0",
"status": "processing",
"createdAt": "2025-12-27T19:19:35.036Z"
},
{
"_id": "695031167d5247d58c029e62",
"project_title": "My Project",
"speed": "1",
"pitch": "0",
"status": "finished",
"createdAt": "2025-12-27T19:18:46.737Z",
"finishedAt": "2025-12-27T19:19:03.426Z"
},
{
"_id": "694b3c1199f08a2ce975b2af",
"project_title": "My Project",
"speed": "1",
"pitch": "0",
"status": "failed",
"createdAt": "2025-12-24T01:04:17.078Z"
}
]
}curl
curl --location 'https://api.narris.io/api/tts-w-vc/logs?page=1&limit=10' \ --header 'Content-Type: application/json' \ --header 'x-api-key: YOUR_API_KEY'
Fetch Text to Speech Voice Cloning By ID
/api/tts-w-vc/{log_id}
This endpoint allows you to fetch the complete details of a text to speech request generated using a cloned voice avatar.
The response includes the original input text, selected avatar, language, synthesis parameters, processing status, and the generated audio output once the request is completed.
Request Body
log_id (string, required)
Unique identifier of the voice cloning text to speech request returned during creation or from logs.
Example: "6943deeac4e97d9166fd1626"
Response
On success, the API returns detailed information about the voice cloning request.
If synthesis is completed, the response includes a downloadable output_file URL for the generated audio.
{
"_id": "6943deeac4e97d9166fd1626",
"project_title": "My Project",
"input_text": "Hello world",
"language": "english",
"avatar": "daaji",
"speed": "1",
"pitch": "0",
"status": "finished",
"createdAt": "2025-12-18T11:00:58.702Z",
"updatedAt": "2025-12-18T11:01:17.255Z",
"finishedAt": "2025-12-18T11:01:17.254Z",
"output_file": "https://lingui-dev.s3.amazonaws.com/text_to_speech_with_voice_over/output/20251218110115_20251218110101.wav"
}curl
curl --location 'https://api.narris.io/api/tts-w-vc/6943deeac4e97d9166fd1626' \ --header 'Content-Type: application/json' \ --header 'x-api-key: YOUR_API_KEY'
Notes for Developers
• Voice cloning requests require a valid reference audio sample to reproduce the target speaker’s voice characteristics.
• Requests are processed asynchronously. Always store the returned log_id to track cloning and audio generation status.
• Voice cloning jobs may remain in pending or processing state longer than standard TTS depending on audio length and model load.
• Use the Fetch Voice Cloning List endpoint to view all cloned voice jobs and Fetch Voice Cloning By ID to retrieve the generated audio output.