Aletheia Support

Send a voice-native turn to the in-product Aletheia assistant.

DARK MVP (issue #2195): normalizes the voice-native transcript and runs it through the SAME answer-core the chat adapter uses, returning a voice-shaped (speech) result. Same gate as the chat sibling — see that operation's description. Binds the real grounded answer core (makeGroundedAnswerCore); the fail-closed denyAnswerCore it originally shipped with was replaced when MNE-1937 landed.

post/aletheia-support/voice

Request

  • Base URL: https://api.mnemom.ai/v1
  • URL: https://api.mnemom.ai/v1/aletheia-support/voice
  • Auth: none required

Request body

transcriptstring required

The caller's spoken turn (ASR transcript). Must be a non-empty string.

call_idstring

Optional voice call id.

localestring

Optional BCP-47 locale.

Response

The core's answer, voice-shaped. refused:true means the core (or the adapter's length guard) withheld an ungrounded answer; speech is then a fixed canned refusal string, never model-generated.

speechstring required
refusedboolean required
refusalReasonstring

Changes

No recorded changes to this operation across all 1 revision of this API.