Clone a voice from an audio sample
Request Body
application/jsonRequiredmetadataMetadataCaller-supplied metadata; ≤16 keys, key ≤64 chars, value ≤512 chars
callback_urlCallback UrlHTTPS URL Beatra will POST the final Task envelope to when the Task reaches a terminal state
callback_signing_key_idCallback Signing Key IdOptional standalone callback signing key. Omit for unsigned callback delivery; requires callback_url when provided.
model_optionsModel OptionsPer-model-family passthrough options; opaque to the platform, validated per model
sampleRequired
SampleClean single-speaker voice sample (uploaded artifact or HTTPS URL), ~10s-5min
display_nameRequired
Display NameMinimum length:
1Maximum length: 255modelModelClone engine; 'auto' lets the platform choose
Default:
"auto"Value in: "auto" | "minimax-voice-clone"languageLanguageOptional BCP-47 language hint for the cloned voice
consent_attestedRequired
Consent AttestedCaller asserts it has the rights to clone this voice. Recorded, not verified.
Header Parameters
X-Request-IdstringOptional client request id echoed in the response.
Idempotency-KeyRequired
Idempotency-KeyMinimum length:
1Maximum length: 128AuthorizationRequired
stringBearer API key.
Clone task accepted; task output carries the new voice_id