Voice Cloning

Create a cloned voice from an audio file. This endpoint allows you to create a new voice by providing a voice sample and reference audio.

post/voices/clone

Request

  • Base URL
    https://api.munsit.com/api/v1
  • URL
    https://api.munsit.com/api/v1/voices/clone
  • Auth
    API key in header x-api-key

Request body multipart/form-data

voice_filestring binary required

The generated preview audio file from the preview API

reference_audio_filestring binary required

The original audio file used for the preview

textstring required

The text used in preview generation

stabilitynumber required

Voice stability (0.0 to 1.0). Higher values produce more consistent output

namestring required

Name for the cloned voice

modelstring required

Model identifier to use for voice cloning

descriptionstring

Description of the voice

genderstring

Gender of the voice (e.g., 'male', 'female')

agestring

Age category of the voice (e.g., 'middle', 'elderly')

languagesstring

Comma-separated list of language codes (e.g., 'ar,en')

dialectsstring

Comma-separated list of dialects (e.g., 'najdi,hijazi')

avatar_urlstring

URL to an avatar image for the voice (you can put your image URL here)

Response

Voice created successfully

idstring uuid required

Unique identifier for the voice record

voice_idstring required

Voice identifier used in API calls

namestring required

Name of the cloned voice

descriptionstring nullable

Description of the voice

genderstring nullable

Gender of the voice

agestring nullable

Age category of the voice

languagesstring[] required

List of language codes supported by the voice

dialectstring[] required

List of dialects supported by the voice

tagsstring[] nullable

Use cases the voice is curated for, as shown in the dashboard filters (e.g., ["conversational"]). null when the voice has not been tagged.

typestring nullable

Voice type

sample_urlstring uri required

URL to the sample audio file

avatar_urlstring uri nullable

URL to the avatar image

stabilitynumber required

Voice stability value

is_clonedboolean

Always true for a voice created by cloning

Changes

    • breaking

      the response's property type changed from string to integer for status

    • breaking

      the response's property type changed from string to integer for status

    • breaking

      the response's property type changed from string to integer for status

    • info

      added the optional property to the response with the status

    • info

      added the optional property to the response with the status