change language
Translates and re-records the speech in the same voices. Every speech clip with words and a voice is translated. A person on camera is dubbed: the translated take goes under the picture, its own sound off, lips unchanged. Text clips, a graphic's text controls and chapter and note markers are translated; brand kit words stay as written. Captions are re-cut from the new audio. Words inside a picture and a graphic with no text control stay; the job's result counts what was translated and names what was left. Saved as a new timeline named "<name> · <Language>" unless as_new_timeline is false. A speaker with words but no voice (an uploaded recording) gets one built from their recording when consent is true; without it those speakers stay as they are and are named in the plan. One price for the whole dub, on the speech length, refunded if the job fails. Requires a transcript first: transcribe_media with timeline_id. A longer take moves later clips and extends the picture under it; each take plays at the old clip's loudness. Returns a job; get_jobs carries timeline_id when the new timeline is ready. Subtitles only: captions translate. Credits.
POST
change language
Authorizations
Headers
Body
application/json
The language to speak. The values here are the whole supported set.
Available options:
en, es, fr, de, it, pt, ja, ko, zh, ar, hi, ru, nl, pl, sv, da, fi, no, cs, sk, hu, ro, bg, hr, uk, el, tr, th, vi, id, ms, fil, ta, te, ml, kn, bn, gu, mr, pa, he, fa, ur, sw, ha, af, ga, cy, is, ca, gl, sl, et, lv, lt, sr, bs, mk, ka, hy, az, kk, ne True records that the user agreed to this statement: "I have the right to clone this voice: it is my own, or the person speaking has agreed to it being recreated and used in this project." Speakers with no voice then get one built from their recording. Omitted, they are left as they are.

