34 reference-to-video (R2V). Optional for image-to-video (I2V) — when34 reference-to-video (R2V). Optional for image-to-video (I2V) — when
35 omitted, the model generates a video from the image alone.35 omitted, the model generates a video from the image alone.
36 36
37* `reference_audios` (array\<object>) — Optional reference audio clips (voice identity) for reference-to-video
38 generation. Only supported by select video models; at most 3 clips.
39 May be provided without \`reference\_images\` (audio-only
40 reference-to-video) — at least one reference of either kind selects
41 the reference-to-video mode.
42
43 * `url` (string, required) — Base64-encoded audio data URL (e.g. "data:audio/wav;base64,...") or an
44 http(s) URL to a downloadable audio clip.
45
37* `reference_images` (array\<object>) — Optional reference images for reference-to-video (R2V) generation.46* `reference_images` (array\<object>) — Optional reference images for reference-to-video (R2V) generation.
38 When provided generates video using these images47 When provided generates video using these images
39 as style/content references.48 as style/content references.