input_audio to POST /api/tts/simple-generate or to an audio content block in an asynchronous job — an arbitrary external URL is rejected with TTS_INPUT_AUDIO_INVALID, because the server validates both host and reserved path.audio must be a data-URL string beginning with data:audio/...;base64,, not a multipart file. Constraints:UPLOAD_TOO_LARGEVALIDATION_TOO_LONGSAFETY_CONTENT_REJECTED with a traceIdduration and URL in the response describe the transcoded file rather than the bytes you sent. Input that ffmpeg cannot parse returns UPLOAD_AUDIO_INVALID.Retry-After. This bucket is separate from the 8-per-10-minutes bucket used by voice creation and style addition.{ status, code, message, requestId? }. code is always the parent code — sub codes only change message and never appear in the body. requestId is present only on reportable-tier errors, so use the X-Vocu-App-Request-Id response header when troubleshooting (it is written unconditionally on every response). See the "Errors" document for the full code reference.