Speech

Complete the open (final) turn of a conversation

Given a conversation, complete its last ('open') turn. A speaker-only open turn is authored (text + audio); an open turn with text is rendered as that speaker, conditioned on the prior turns (contextual TTS).

post/v1/converse

Request body

modelstring nullable

Public model id (see GET /v1/models). Omit/null for the default model.

Example request

{
  "model": "kalpa-tts-beta-v0.1"
}

Response

Successful Response

request_idstring required

Correlation id; identical to the X-Request-ID response header.

modelstring required

Resolved public model id that served the request.

metaobject

Example response

{
  "reply": {
    "audio": {
      "sample_rate": 24000
    }
  }
}

Changes

Changed in 2 of the 4 revisions of this API.32

    • removed the request property params/top_k

      request-property-removed

    • removed the request property params/penalty_window

      request-property-removed

    • removed the request property params/repetition_penalty

      request-property-removed

    • the max_new_tokens request property default value 512 was removed

      request-property-default-value-removed

    • request property params/max_new_tokens list-of-types was widened by adding types null to media type application/json

      request-property-list-of-types-widened