Change Voice

One video in. The same video out, with the speech re-performed by a voice you chose.

The picture never moves. The timing never moves. What changes is who is speaking, and the entire craft of this skill is in three decisions the endpoint cannot make for you: which voice, which spans of audio to replace, and whether the result is actually good. The HTTP call in the middle is one request.

Every HTTP mechanic here belongs to the pack, not to this skill. Auth, strict bodies, status codes, rate limits and error envelopes are written out once in skills/novoads-api/SKILL.md and its reference.md. Read those for mechanics; this file names the endpoint and the fields that matter to a re-voice.

Before anything: this runs on a Novoads account