Create voice
Submits a request to create a voice given configuration data and some source audio.
The metadata field must come before the files in your request.
For Professional Voices, at least 5 minutes of source audio is required for a clone; the more, the better, up to 250MB total source file size.
For Instant Voices, as little as 30 seconds of source audio gets you an instant clone.
For more on voices in general, visit our guide.
Headers
Your API key; get it from your LMNT account page.
Body
Information about the voice you are creating; a stringified JSON object containing the following fields:
namerequired: string; The display name for this voiceenhancerequired: bool; For unclean audio with background noise, applies processing to attempt to improve quality. Default isfalseas this can also degrade quality in some circumstances.typeoptional: string; The type of voice to create. Defaults to instant.genderoptional: string; A tag describing the gender of this voice. Has no effect on voice creation.descriptionoptional: string; A text description of this voice.
One or more input audio files to train the voice in the form of binary wav, mp3, mp4, m4a, or webm attachments.
- Max attached files: 20.
- Max total file size: 250 MB.
- Professional voices require at least 5 minutes of source audio to train from.
Response
Voice details
The unique identifier of this voice.
The display name of this voice.
The owner of this voice.
system, me, other The state of this voice in the training pipeline (e.g., ready, training).
A text description of this voice.
A tag describing the gender of this voice, e.g. male, female, nonbinary.
Whether this voice has been starred by you or not.
The method by which this voice was created: instant or professional.
instant, professional Was this page helpful?