Extract Sound Effect
extract_sound_effectPull one described sound out of your video, like "keyboard clicks", "camera shutter" or "page turning", and split it into single effects to hear, trim and save. Use the video already in the chat: put its file id or name in video_url; when it was sent earlier, not with the latest words, find it first among what was sent before. Never ask the person to send it again. Give the sound in a few words, and start_seconds and end_seconds when the person says where it is (leave them out to search the whole video). Priced at 1 token for each 10 seconds searched. It answers with a job_id: the clips come into the chat by themselves when done (about a minute). For where a job is, or to stop it, use sound_extraction_status with the job_id. The same request again answers the job already made and charges nothing. Clips are split where the sound goes quiet, which is a suggestion: music or speech under the sound can leave traces. When separation keeps too little of the sound (more than 10 dB under that part of the video) or fails, the clips are cut straight from the video's own sound instead: the answer says from "cut from the video", tell the person that anything else playing at that moment is in them too. A cut holds every sound in that part, one clip per sound, whatever words were asked: never ask again for other sounds in the same part, and give each clip its own name from where it sits. A failed separation is not charged.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| again | No | true only when the person asks to run the same extraction again (charged again). | |
| sound | Yes | The sound to pull out in the person's own words, unchanged (they become the clip's name), e.g. "keyboard clicks". | |
| video_url | Yes | The video in this chat by its file id or name, or an https link. | |
| end_seconds | No | Optional, where it ends, in seconds. | |
| start_seconds | No | Optional, where the sound starts in the video, in seconds. |