Write a finished interview up as prose, in first, second or third person.

BCP-47-ish language code (e.g. 'en', 'zh-cn') for localized messages.

The end-user's username.

The end-user's password on first sign-in. After login/register, send the returned session token (JWT) here instead — the field accepts either, and reusing the token keeps raw passwords out of your storage.

Identifies one interview. Returned by start_voice_interview and required by every later call.

Ask for a consciousness by name instead of writing up an interview: returns the third-person description of that consciousness, if one has been produced. Any authenticated caller may ask. Only the third-person form is available this way; the first- and second-person forms address the interviewee and are theirs alone.

The owner's answer to whether other people may read this consciousness's description. True publishes the description already written for it; false withdraws it and erases the text. A newly written description is never readable by anybody else until this says so, so the person can read what is being said about them first.

Which voice to write in. first_person reads as the user themselves and is what a mind-data upload wants; second_person addresses them; third_person describes them for a reader who was not present and leaves out anything they would not want quoted.

Whether the call succeeded.

Human-readable reason when success is false.

Identifies one interview. Returned by start_voice_interview and required by every later call.

Which voice the write-up was produced in, echoing the request.

The finished interview, written as prose.

Which mind-data category this interview produces — memory or persona — so an upload can be filed without guessing.

True when a written-up version could not be produced and report_text is the answers the user gave instead, joined in the order they were given. Say so before showing it, rather than presenting it as a finished piece of writing.