Changes to Design a new voice from a character description (such as "deep-voiced warrior" or "cheerful young girl"), a character image, or both, and have it speak a short line of text, returning a sample of that newly created voice. text is required, plus voice_description or image (an image of the speaking character, given as a URL or base64, makes the description optional); the spoken text is limited to 100 characters or the call returns HTTP 400, and type selects "human" or "non-human" voices. The job result is a single audio result containing the URL of an MP3 or WAV file (the URL's extension, .mp3 or .wav, says which). Credits are held when the job is accepted and refunded if it fails or is cancelled. 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 listGenerations (type audio). Requires an API key (user scope). The call returns 202 with a job id - poll `GET /assets/jobs/{id}`, honouring poll_after_ms or long-polling with wait=30, until status is succeeded; its result field is exactly the response documented for this operation. Synchronous responses are deprecated but still supported: pass `async: false` to block until the result is ready and receive it as the response body. 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).