Timed text overlays are lines you time, not auto-captions
add_timestamped_captions burns copy you wrote at start_sec and end_sec. It does not transcribe speech.
add_timestamped_captions burns copy you wrote at start_sec and end_sec. It does not transcribe speech.
spawn_background_task is several tools in one async job. Treating a single generate as a pipeline wastes credits.
edit_video is one EDL pass. Chaining trim, attach, and caption as if they were this job wastes credits.
get_social_analytics reads your connected accounts. It is not analyze_trend on someone else's post.
clone_voice_from_audio mints a voice_id you keep using. It is not a TTS pass and not a voice you describe in words.
connect_social_account returns a link you finish yourself. It does not publish, schedule, or pull analytics.
cover_music needs a source URL and a new style. It is not generate_music from a blank prompt.
create_ai_movie is a scene list, a draft, then a stitch. One long text-to-video prompt is a different job.
edit_previous_generation is a delta on something you already made. A new prompt from scratch is a different charge.
generate_image_from_image isolates a still. Treating that cutout job as a clip key or a restyle wastes credits.
start_template_run needs the template's inputs, usually a photo. It is not a cloned workflow and not a scene-planned movie.
search_broll finds reaction clips you can overlay. Generating a presenter is a different model row.
separate_music_vocals splits a Versely Suno generation into stems. Any mixed URL is isolate_audio, not this job.
create_share_link is a review URL with a preview card. It is not a social post and not a project save.
generate_video_from_image in motion-control mode needs a still and a driving clip. Prompting a dance without that clip wastes credits.
create_slideshow_from_uploaded_images uses your photos in order. It does not generate new slide art.
upscale_video does not rewrite the shot, add seconds, or invent a new take. A regenerate is a different job.