Voice commands: clone, retire

Reference for Voice, one group of Voice commands.

Voice.clone

Clone trains a Voice from a real speaker’s recordings after the speaker records Consent in that same voice. Verb page.

Text

npx startup-builder do Voice.clone --json '<input>' [--try | --send | --do]

Emits Voice.cloned.

Inputs

Input	Type	Required	Description
`speaker`	Person	required	The person whose voice it is.
`samples`	list of File	required	Recordings of the speaker.
`consent`	Consent	required	The speaker’s Consent, spoken in the voice being cloned.
`scope`	`string`	required	Who may speak in it.

Returns

Output	Type	Required	Description
`voice`	Voice	required	The Voice, `training` until the upstream finishes.

Refuses when

Check	Error	Fix	Then call
The key is valid, but its scopes do not allow this operation.	`forbidden`	Use a key whose scopes cover the operation, or ask an owner of the namespace to grant them.	None.
The Consent is missing, withdrawn, or not spoken by the speaker	`refused`	Clear what the check names, then call it again.	None.

Example

Terminal

npx startup-builder do Voice.clone --json '{"speaker":"person_sLqbXbW683","samples":["file_V1AuhyCTsH"],"consent":"consent_lMkrg7nUGY","scope":"studio"}'

Voice.retire

Retire deletes a Voice’s trained copy at the upstream and refuses new speech in it, keeping the record and every File made. Verb page.