Design a new voice from a character description (such as "deep-voiced warrior" or "cheerful young girl") and have it speak a short line of text, returning a sample of that newly created voice. Both voice_description and text are required, the spoken text is limited to 200 characters or the call returns HTTP 400, and type selects "human" or "non-human" voices. Synchronous until September 10, 2026: the call blocks until generation finishes and returns a single audio result containing a URL; there is no separate polling step. Credits are charged on success. Use this to invent and audition a voice from a description; use createSpeech for text-to-speech that clones a specific voice from an audio sample, and createSpeechPreset for text-to-speech using a named preset voice. Pass an optional request_id to tag the result so you can locate it later via `GET /assets/audio/results`. Requires an API key (user scope). Async is the intended integration pattern: pass `async: true` and the call returns 202 with a job id - poll `GET /assets/jobs/{id}` (`getApiJob` in MCP), honouring poll_after_ms or long-polling with wait=30, until status is succeeded, whose result field is exactly the response documented for this operation. Synchronous responses are deprecated: they remain the default until September 10, 2026, after which requests default to async and return 202 with a job id; set `async: false` explicitly to keep synchronous behavior during and after the transition. Synchronous calls run on the same queue: the response carries an X-Ludo-Job-Id header, and a job still running after 15 minutes comes back as 202 with the job instead of an error. Each account may have up to 50 generations queued or running at once via the API; a request beyond that returns 429 (code PENDING_JOBS_LIMIT).