gen_characters

io.github.poweredbyGEN/gen-mcp-server · Verify this server

Characters: one person each, with looks (images of the person) and talking characters (talking videos of the person with their voice, generated from a look or uploaded). For 'create a character', op=create is the first call — do not list characters or read gen_discover agent.profile_photos first (those are the agent profile photos, not characters). Reads (a viewer is enough): list (source my | library | all, default my; query searches names), get (character_id: its looks, each look's talking characters, the uploaded talking characters, the talking characters still generating and the primary voice), get_talking_character (one talking character with its clips). create makes a character from an image content resource (its original look) or a video of a person: the video becomes an uploaded talking character, its first frame the first look (the cover), and its audio is cloned into the character's primary voice. Cloning is a paid job priced before it runs (it needs 30 seconds of speech); clone_voice false skips it. clone_voice true refuses a video without audio or too short; without clone_voice such a video is created without a voice and voice_clone_message says why. create answers look_id, talking_character_id, voice_id (null until the clone finishes, then the character's primary_voice), user_job_ids (poll with gen_discover generation) and voice_clone_status. name defaults to the file name. upload_look adds an image and upload_talking_character adds a video to a character (clone_voice true also clones its voice into that character's primary voice, same rules and answer fields as create; off by default); upload or import the file first with gen_asset_action. create_talking_character makes a talking character from a look, lip-synced so it is saved with its voice: clips is 3 to 10 clips, each {prompt, duration 5 or 10}, and the look is the start and end frame of every clip; aspect_ratio 9:16 | 16:9 | 1:1 sets its shape (default 9:16). script is optional (a default line is used when blank) and voice {voice_id, provider} defaults to the character's primary voice; with neither a voice nor a primary voice the call is refused. edit_talking_character saves a NEW talking character from a generated one and keeps the original: send the full clip list in the new order (reorder by order, delete by leaving a clip out), where {from_position} keeps that clip of the source. A kept clip whose prompt, duration and aspect_ratio are unchanged is reused: no render, no charge; give it a new prompt or duration to regenerate it. A {prompt, duration} item without from_position is a new clip and renders. The source's aspect_ratio applies unless one is sent. Every talking character carries aspect_ratio (9:16 | 16:9 | 1:1, or null when an uploaded video is none of them). Both are paid jobs priced before they run; they answer generation_id to poll with gen_discover generation, and op=get lists the talking character under generating_talking_characters until it is ready. Library characters are read-only: copy_to_mine makes your own copy, and create_talking_character or edit_talking_character on a library character saves into your copy. rename takes character_id and name, plus look_id or talking_character_id to rename that item instead. set_primary_voice sets the voice pre-selected for this character (voice {voice_id, provider}). delete_character, delete_look (its talking characters stay) and delete_talking_character are permanent: the first call answers CONFIRMATION_REQUIRED with would_destroy and confirm_token; repeat the call with confirm_token only after the user agrees. A talking-head video from an existing character is instead gen_vidsheet_action op generate, creation_card_type video_from_avatar (avatar_id = the character_id + video_url + audio_url).