generate audio
Generate audio: voiceover (a script read by a voice from list_models type voice, in any of the listed languages), music (a prompt, or lyrics on the models that take them), or sound_effect (a prompt). Voiceover and sound effects finish inside the call; music runs as a job. get_jobs returns the item for both. Credits are charged before the provider runs and refunded if it fails without output. Credits.
Authorizations
Headers
Body
voiceover: the script, read as written (spell numbers, symbols and names as said). Bracketed tags direct the delivery unspoken: [whispers], [laughs], [excited].
music or sound_effect: the prompt. For music: the mood asked for, steady or building; under a voice, sparse, with no lead in the vocal range and no crescendo. On google music, timed sections ("[0:00 - 0:10] Intro: soft lo-fi beat") are followed, so the track's sections fall on the cut; on minimax a named key and tempo ("E minor, 90 BPM") are followed.
music: the provider, default google. google and minimax take lyrics and set their own length (about 3 and 6 minutes); elevenlabs takes a duration. google follows a timed arrangement in the prompt, minimax a named key and tempo. estimate_cost quotes each.
google, minimax, elevenlabs voiceover: the language to speak in; the values here are the whole supported set. Every voice speaks all of them, so the voice is chosen for its character and this for its language.
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 
