GoFaceless

Use this to read one existing chat video session once: when the user asks "how is my bakery video going?" or "is it done yet?", or when you need its pending action or state version to make a decision. Do not poll: the GoFaceless card from start_video_session or show_video follows its progress and plays the video when it is ready. Only where no GoFaceless card is shown, check again after poll_after_ms while next_action is wait, and never start a duplicate while waiting. When next_action is none, nothing can continue the session here: give the user the link in its status and send no instructions. Returns compact text-only status. Do not use for showing or playing a video (use show_video), for template videos (use get_template_video), or for listing videos (use list_video_sessions).

get_video_session

Use this when the user wants to see their GoFaceless videos as a list: "show my latest videos", "open my GoFaceless library", "what were my first two videos?". Shows them as one grid card in which every video plays. Set order to oldest for their first videos and limit to the number asked for. That card is the whole answer; do not open each video with show_video. Do not use for watching one video the user names (use show_video) or for checking one video's progress (use get_video_session).

list_video_sessions

Use this when the user wants to put themselves, a friend, or a partner into a viral video template or trend from a photo but has not picked one, or asks which templates there are: "what templates do you have?", "show me the anime templates", "something for a couple", "make me a glow-up video". The catalog adds new viral templates and trends often: when the user names a template, trend, or viral video that you do not know, call this with query set to that name to look it up. Templates sit in the same categories as gofaceless.ai/templates (Anime, Fashion, Culture, Cartoon); for a kind of template, pass the user's words as query, or pass templates with the ones you mean, so the card shows only those. Lists the templates, who is in each, how many photos each takes, and their options. Do not use when the user names a template you already know (for example Burning Bridges, Hotel Lobby, Bulin 47, Özil Goal): call prepare_template_video directly. Not for editing a still picture; the result is a short video.

list_video_templates

Use this when the user asks to see the content photos of one of their AI Influencers, or before making a pack to learn its price: "show Maya's photos", "what posts does franck have?", "how much is a photo pack?". Shows the photos with their captions in a card, and gives the credits per photo and how many photos the account can still make today. Do not use to make new photos (use make_influencer_photo_pack).

list_influencer_photos

Use this when the user asks what GoFaceless videos they have ("my videos", "what did I make?"), or to find the ID of a video or draft they name. Lists them newest first with their status.

list_videos

Use this when the user wants to use one of their saved AI Influencers (a character they created on GoFaceless, with a face, a voice, and looks) or asks which influencers or looks they have: "show my AI influencers", "put Maya in Hotel Lobby", "which looks does franck have?". Lists each influencer with their ready looks as pictures. To star one in a template, pass the look IDs to prepare_template_video as influencer_look_ids; no photos are needed. Do not use to create an influencer (use create_ai_influencer) or to see an influencer's content photos (use list_influencer_photos).

list_ai_influencers

Use this when the user wants to carry on, check, or pick one of their existing animated series and its series_id is not in this chat: "continue my cartoon series", "what happened to my pizza series?", "write the next episode of my show". Lists the account's series, most recently active first, with parts made, the latest part's status, and whether the next part can be written. Spends nothing. Do not use to start a new series (write_series) or to list finished videos (list_video_sessions).

list_series

Use this when the user wants new ready-to-post photos of one of their AI Influencers: "make Maya a gym photo pack", "six photos of franck for Instagram", "a weekend-in-Paris pack". It costs credits: get credits_per_photo from list_influencer_photos, tell the user the price of the pack (count x credits_per_photo), and call this only after they approve it, with approved_credits set to that price. Each photo puts them in one of their looks somewhere new, with a caption in their voice. Credits for photos that cannot be drawn are returned. The card shows the photos as they are drawn (a minute or two each). Do not use to see existing photos (use list_influencer_photos) or for videos.

make_influencer_photo_pack

Use this after the user approved a priced plan of several chat videos: "make all five", "plan this week's videos and make them", "yes, start the plan". Price the plan with quote_video_plan first and show the total; after the user approves it, call this with approved_credits set to that total. Starts up to five faceless videos at once, in plan order, each only if it fits within approved_credits and the credits left; the rest are reported as not started. Shows them together in a grid that updates until each is ready. Do not use for a single video (use start_video_session) or before the user approved the total.

start_video_batch

Use this only after the user approved the exact price of a series part shown with its script ("yes, make it", "make episode 1"). Spends that many credits to make the part as an animated video, at the approved price and for the exact draft that was priced; it is refused if the price went up or the script changed since. Returns a job ID and shows the part's progress and video in a card. Do not use without that approval, or for template or faceless videos.

make_series_part

Use this only after the user approved the exact price from quote_ad_video ("yes, make the video ad", "go ahead with that video"). Makes one short video ad from a finished static ad (the same product, words, and brand, ending on the ad; a promo is 16:9 and ends on the product name) and spends the approved credits once; a retry with the same arguments never spends them twice. It takes several minutes; list_ads shows it when ready. Do not use for chat session videos or template videos.

make_ad_video

Use this only after the user approved the exact price from quote_ads ("yes, make them", "go ahead with the 8 ads"), with the arguments quote_ads gave. Makes finished static ads for each product (feed 4:5, square 1:1, and story 9:16 sizes) in the brand's colours, with words taken from its own page, and spends the approved credits once; a retry with the same client_request_id never spends them twice. Returns right away: writing the ads takes a few minutes, and the card shows each ad as it is drawn. Do not use for template videos or faceless video sessions (start_video_session).

make_static_ads

Use this only after the user said yes to a draft's exact price ("go ahead", "make it", "yes for 300 credits"). Makes that draft version and spends at most the credits they saw. If the price or the plan changed, no credits are spent and the new version or price comes back to show them. Approving the same version again returns the same video.

approve_video

Use this only after the user approved the exact credit price from prepare_template_video or prepare_trend_video: "yes, make it", "go ahead for 465 credits", "make the video". Spends that many credits to make the template video, with the people and options from that result unchanged and approved_credits set to the approved price. Returns a job ID; the card then shows the progress and plays the video when ready, so do not poll get_template_video; call it only when the user later asks about the video. Do not use before the user has seen and approved the price, or to start again a video that is still being made.

start_template_video

Use this when the user asks who is in one of their shows (an AI Series), or wants one of their AI Characters added to or removed from it ("put Maya in my bakery series"). Lists their shows, shows one show's cast, or adds or removes a character, so every later part keeps the same cast.

manage_cast

Use this whenever the user wants a new GoFaceless video, whatever kind: themselves in a template from their photo ("put me in Hotel Lobby", "make a glow-up video of me"), their face in a pasted video link, a faceless or narrated video from an idea ("a 30-second video about saving money"), a whiteboard explainer, an ad, an AI Series show or its next part, several videos at once, or another shape or length of a video they have. Returns a free draft with its credit price, or what it still needs (photos, or the page that makes that kind of video). Show the user the draft and price; nothing is made and no credits are spent until approve_video.

plan_video

Use this when the user wants to be in a GoFaceless template they name (for example Burning Bridges, Hotel Lobby, Bulin 47, Özil Goal, or another template or viral trend) with their photo or AI Influencer, even without saying "video" or "GoFaceless": "put me in the Hotel Lobby template with this photo", "do Burning Bridges with me and my sister", "same template with my last photo". For a template you know, call this straight away without listing templates first; for a name you do not know, look it up first with list_video_templates (query set to that name) and then call this with the template it returns. These templates are videos, so answer with this tool, not with a drawn image. Adds the user's photos or AI Influencer looks (one per person to replace), starts a free preview still of them in the template (free on every plan), and gives the exact credit price of the full video without spending anything. For "my last photo" or "the same photo" with no photo IDs in this chat, set recent_photos instead of asking for the photo again. Confirm the user owns or has permission to use each photo. Show the price and ask the user to approve it before start_template_video. Do not use for browsing templates (use list_video_templates) or for a faceless video from an idea (use start_video_session).

prepare_template_video

Use this before asking the user to approve any chat video that will spend credits: one video before start_video_session, or a plan of up to five before start_video_batch. For example "how much would a 30-second video cost?", "price these five videos", "can my credits cover this plan?". Gives each video's credit price, the total, and whether the account has enough. Spends nothing. Do not use for template videos (prepare_template_video gives their price) or for the account balance alone (use show_account).

quote_video_plan

Use this when the user wants one of their finished ads as a short video ad ("a video ad for this product", "turn this ad into a video", "a presenter video of this ad", "a promo video for my site"). Needs an ad_id from list_ads or make_static_ads; a promo of the whole site takes the site_id from read_brand_site. Gives the exact credit price of that video (cut: the ad filmed; presenter: a creator says the ad's line; motion: the product shot moves with a camera preset; promo: a 16:9 film from the brand's site, one word on each music beat over its own photos, ending on the product name) and lists the motion presets; spends nothing. Show the price and ask the user to approve it before make_ad_video. Do not use for a video from an idea or script (start_video_session) or for putting the user into a template.

quote_ad_video

Use this before making static image ads (Ads Studio): right after read_brand_site with its site_id and the product_ids the user picked, or for a product the user describes with its photo attached ("Instagram ads for my product"). Gives the exact credit price and the account's credits; spends nothing. Set videos_per_product when the user also wants video ads with the set ("ads and a video ad for this product"). Show the price and ask the user to approve it before make_static_ads. Do not use for template videos or chat video sessions.

quote_ads

Use this when the user wants ads for their shop, brand, or product and gives its website or a product page link ("make ads for my shop https://…", "Instagram ads for my product https://…", "Facebook ads for this store"). Reads the public site into the brand (name, colours, voice) and its products with their photos, and shows the products in a card. Spends nothing. Reading takes one or two minutes, so it may answer that it is still reading: the card shows the products when they are found, and calling it again with the site_id it gave checks on the read. Next, call quote_ads with its site_id and the products the user picks. Do not use for general web browsing, for putting the user into a video template, or for a faceless video about a topic (start_video_session).

read_brand_site

Use this when the user asks whether a GoFaceless video is ready, how far along it is, or what a draft says ("is my video done?"). Reads one draft or video: its plan and price, or its progress and result. The card already follows a video being made, so never call this just to poll.

get_video

Use this when the user wants a finished GoFaceless video in another shape or length: "make a square version", "a vertical one for TikTok", "a 15-second cut". Makes a new video from the same setup with that one change; it costs credits like a new video of that shape or length (quote_video_plan gives the price), so tell the user and confirm first. Do not use for edits to the same video (use send_video_instruction) or for template videos, which keep their own format.

make_video_variant

Use this when the user wants to watch a draft of a chat video session before the final export: "render a preview", "let me see scene 2", "preview the first three scenes". Queues a state-bound scene, range, or full preview through the existing GoFaceless render gates. Do not use for a finished video (use show_video), for the final MP4 (use export_video), or for a template preview still (use get_template_preview).

render_video_preview

Use this when the user wants to change or steer a chat video session that already exists: "make the intro shorter", "use a calmer voice", "swap scene 3 for a beach shot". Sends their words to that session's GoFaceless agent, which works within the credits approved for the session. Do not use to start a new video (use start_video_session), to approve or reject a pending step (use decide_pending_action), for template videos, or when the session's next_action is none (an instruction cannot continue it).

send_video_instruction

Use this when the user wants a link to share a finished GoFaceless video: "share my video", "give me a link to send my friends", "I want to send it on WhatsApp". Creates a public page anyone with the link can watch, or returns the existing one, and the card shows share buttons. Only for finished videos; the owner can turn the link off in GoFaceless. Do not use for the MP4 file (use export_video) or for a video still being made.

share_video

Use this when the user wants to see or watch one of their GoFaceless videos: "show me my bakery video", "play my last video", "let me watch it". Opens the video in a card that plays it once it is ready, or shows its progress until then. Omit session_id for the latest video. Only for one video the user asked to watch: never call it for each video after list_video_sessions, whose grid already plays them. Do not use for status-only checks (use get_video_session) or for template videos (use get_template_video).

show_video

Use this when the user asks about their GoFaceless account: "how many credits do I have?", "what plan am I on?", "when do my credits renew?". Shows the plan, credits left, monthly usage, renewal date, free previews left, and recent spend in a card. Do not use for the price of a particular video (prepare_template_video and quote_video_plan give exact prices).

show_account

Use this when the user asks to see their ads or whether their ads are ready ("show my ads", "are my Instagram ads done?"). With batch_id, shows that set of ads; without it, the latest ads. Shows the ad images and their video ads in a card that updates itself, so call it once per question, never to poll. Do not use for chat session videos or template videos (list_video_sessions, get_template_video).

list_ads

Use this when the user wants a new short video made from an idea, script, topic, product, or reference: "make a 30-second faceless video about budgeting tips", "a UGC-style ad for my candle shop", "a top-5 listicle about Lisbon". It spends credits (except when get_video_capabilities or quote_video_plan says an explainer costs this account 0 credits: start that one straight away, without a budget), so price it first: call quote_video_plan with this one video (the same video_format, target_duration_seconds, and orientation), show the user that credit price, and call this only after they approve it, with budget.max_credits set to the approved price so the session never spends more. Starts exactly one durable session, in autonomous mode unless the user asks for review checkpoints (controlled), and returns at once with its session ID; its card shows progress and plays the video when it is ready, so do not poll get_video_session afterwards. Do not use for putting the user's own face or photo into a template or trend (use prepare_template_video), for several planned videos at once (use start_video_batch), or for another shape or length of an existing video (use make_video_variant).

start_video_session

Use this when the user wants to take back the latest change to a chat video session: "undo that", "go back to the previous version", "revert the last edit". Restores the captured state from before that change; read the current session first and provide its exact state version. Do not use for older changes, to cancel a video being made, or for template videos.

undo_last_video_change

Use this when the user wants a cartoon or animated series, a story told in episodes, or a skit or short drama acted out by two characters: "make a cartoon series about my cat and my dog", "episode 1 of my story about a haunted bakery", "an animated skit with two characters arguing about pineapple pizza", "a short drama series". Plans the season and writes the Part 1 script without spending credits, returns the script to show the user, and the credit price of making Part 1 as a video. Nothing is spent. Do not use for faceless explainers, ads, or narrated videos about a topic (start_video_session), or for putting the user's own face or photo into a template or trend (the template tools).

write_series

Use this when a series part is finished and the user wants the next episode: "write part 2", "what happens next?", "next episode where they get caught". Writes the next part's script from the season plan without spending credits, and returns it with its price. Do not use before the latest part is finished, to change the current script (revise_series_script), or to start a new series (write_series).

write_next_series_part