Skip to content

Personalized Voice Creation

This API guide will instruct you on how to create a personalized voice.

Quick Start

Let’s explore how to create a personalized voice to use in bulk templates and bulk video requests. 🎧✨

Create Personalized Voice

A personalized voice is a customized clone of a user's voice, tailored to reflect their unique tone, accent, and speech patterns. This allows for a more personal and recognizable auditory experience, suitable for applications ranging from branding and assistive technologies to entertainment and personal use.

This API helps You to create a personalized voice. In the payload, the most important key is 'audio' file, which should be included as per specific guidelines. The audio file must be between 30 seconds and 10 minutes in length. Please refer to the guidelines for detailed requirements.

Send audio file and other information in api as multipart/form-data. See below curl sample for keys name.

In the response, you will receive details about the created voice, including its 'id', 'name', 'gender', 'user_id', and 'status'. The quality of the personalized voice response is directly influenced by the quality of the provided audio file.

To check the status of your personalized voice use audio status API

curl --request POST  \
     --url 'https://api.immersive-fox.com/v1/voice_generation/create_personalized_voice/'  \
     --header 'X-Api-Key: <your-api-key>'  \
     --header 'Content-Type: multipart/form-data' \
      -F 'audio_file=@my_audio.mp3' \
      -F 'gender=Male' \
      -F 'name=John Calm' \

{
    "id": 362,
    "name": "John Calm",
    "gender": "Male",
    "user": 31,
    "status": "Created",
}