Create Generation

Create a lip sync generation with application/json — provide each input by url or by assetId from an uploaded asset. For reusable or large local files, upload them first with POST /v2/assets/upload and pass the returned assetId; see Asset Uploads. Use the multipart “Create Generation with Files” form only when uploading direct audio, video, or image file fields; it has a 5 GiB per-file application parser limit, subject to your plan and any lower proxy limits. Nested fields such as input, options, segments, dubParams, and dialogueEdit must be JSON strings in multipart requests. If a text input requires speech synthesis and the ElevenLabs provider is temporarily unavailable, the request returns errorCode elevenlabs_service_unavailable: 504 for provider timeouts and 503 for other provider outages for unkeyed requests. Keyed uncertain outcomes return 503 IDEMPOTENCY_OUTCOME_UNKNOWN instead. An API-key request that passes dialogueEdit is refused with errorCode dialogue_edit_retime_required (422) when the organization’s rollout lacks segment lipsync and section expansion. A dialogueEdit that removes more speech than the surrounding footage can absorb returns errorCode dialogue_edit_removal_too_large (422). When the failing section can be identified, dialogueEditSection on the error names it; change it and create a new preview before submitting again. Retrying the same preview fails again. Send the optional Idempotency-Key header on the first request and reuse it with the same payload on retries. An accepted replay returns 200 with the original generation’s current state and Idempotency-Replayed: true. See Idempotent Requests for key validation, conflicts, retention, and uncertain-outcome recovery.