Create a cloned voice
Clone a voice from an audio sample. The sample must be Base64 encoded and 1 KB to 25 MB. MP3, WAV and WebM are accepted; a non-audio body is refused.
A name for the cloned voice, 1 to 100 characters.
Base64-encoded audio, 1 KB to 25 MB (MP3, WAV or WebM).
Optional original filename, for your reference.
Optional description.
Required and must be true: you confirm you have the right to clone this voice.
curl -X POST 'https://omnidim.io/api/v1/voices' \ -H 'Authorization: Bearer YOUR_API_KEY' \ -H 'Content-Type: application/json' \ -d '{ "name": "Front desk", "filename": "sample.mp3", "language": "en", "gender": "female", "consent": true }'
BearerAuthAuthorizationBearer <token>Bearer token authentication. Obtain your API key from the OmniDimension dashboard.
Idempotency-Key?stringOptional. Send a unique value per clone; a retry with the same key and body returns the first clone instead of creating a second. Every clone costs money at the provider, so this makes a retry safe. Up to 255 printable characters.
application/jsonname*stringA name for the cloned voice, 1 to 100 characters.
clip*stringBase64-encoded audio, 1 KB to 25 MB (MP3, WAV or WebM).
filename?stringOptional original filename, for your reference.
description?stringOptional description.
language?stringA short language code for the voice. Defaults to en.
gender?stringThe voice's gender. Defaults to female.
"female""male""female"consent*booleanRequired and must be true: you confirm you have the right
to clone this voice.
Response body
application/jsonThe clone was accepted and is being created. Poll the status until it
is ready or failed.
application/jsonvoice?A voice cloned from an audio sample. Created asynchronously: status is
processing until the provider finishes, then ready or failed.
voice_id is the provider id an agent uses, and is null until ready.
Was this page helpful?