Endpoints
Voice Cloning (BETA)
Create, delete, or edit custom TTS voices.
POST
Header
string
required
Add your API token here. You can find it by reading the /authentication page.
Body
string
required
The action to perform. Must be one of:
create, delete, or edit.create Action Parameters
string
required
Base64 encoded audio file (WAV or MP3). Must be between 30 seconds and 5 minutes in length and under 10MB.
string
required
Name for the custom voice. Must be between 3 and 50 characters.
string
required
The language of the voice. Must be one of the supported languages.
delete Action Parameters
string
required
The ID of the custom voice to delete.
edit Action Parameters
string
required
The ID of the custom voice to edit.
string
New name for the custom voice. Must be between 3 and 50 characters.
string
New language for the voice. Must be one of the supported languages:
Response
create Action Response
string
Unique identifier for the created voice.
string
Name of the custom voice.
string
Language of the voice.
string
URL to the training audio file.
string
URL to a sample generated using the voice. This counts towards your character usage.
delete Action Response
string
Confirmation message of the deletion.
edit Action Response
string
ID of the edited voice.
string
Updated name (if changed).
string
Updated language (if changed).
string
New sample URL (if language was changed). This counts towards your character usage.
Limitations
- Voice creation is limited based on your subscription plan
- Audio files must be between 30 seconds and 5 minutes in duration
- File size limit is 10MB
- Voice names must be between 3 and 50 characters
- Only WAV and MP3 file formats are supported
Supported Languages
- English v3 (New)
en-v3- Our newest English voice model has greatly improved quality and more natural sounding speech.
- English v2
en-v2 - English v1
en - Spanish
es - French
fr - Japanese
ja - Korean
ko - Italian
it - Polish
pl - German
de - Portuguese
pt - Arabic
ar - Dutch
nl - Russian
ru
