テキストから効果音を生成する
Creates an asynchronous sound-effects generation task (`elevenlabs-sfx-v3` or `auto`, 0.5 to 30 seconds). Charged per requested audio second (rounded up) or 5 seconds when `duration_seconds` is omitted. When the task succeeds, `output` contains `{type: "sound_effects", model, loop, audio: {url, artifact_id, duration_seconds, mime_type, size_bytes}}`.
以下のエンドポイント仕様(パラメーター、リクエスト、レスポンス)は英語の原文です。フィールド名は API と同じです。
Request Body
application/jsonRequiredmetadataMetadataCaller-supplied metadata; ≤16 keys, key ≤64 chars, value ≤512 chars
callback_urlCallback UrlHTTPS URL Beatra will POST the final Task envelope to when the Task reaches a terminal state
callback_signing_key_idCallback Signing Key IdOptional standalone callback signing key. Omit for unsigned callback delivery; requires callback_url when provided.
promptText description of the sound effect or ambient audio to generate (1-2000 characters).
1Maximum length: 2000modelModelSound-effects model identifier, or 'auto' for automatic selection.
"auto"Value in: "auto" | "elevenlabs-sfx-v3"duration_secondsDuration SecondsTarget duration in seconds (0.5-30.0). Omit to let the model choose duration automatically.
loopLoopWhen true, generate a seamlessly looping sound effect or ambient bed.
falseprompt_influencePrompt InfluenceHow strictly generation follows the prompt (0.0-1.0, default 0.3).
0.3Minimum: 0Maximum: 1formatFormatOutput audio container/encoding format.
"mp3"Value in: "mp3" | "wav" | "opus" | "pcm"model_optionsModel OptionsOptional model-family-specific options (for example, {"elevenlabs": {...}}). Unrecognized keys emit an option_ignored warning.
Header Parameters
X-Request-IdstringOptional client request id echoed in the response.
Idempotency-Key1Maximum length: 128AuthorizationBearer API key.
Task accepted
最終更新