# Makemancer > Generate and edit images, video, voiceovers, music and sound effects from Claude, ChatGPT and Codex. Pay per generation with credits. Makemancer is a remote MCP server that adds image, video, speech, music and sound effect generation and editing to AI apps: Claude Code, Claude.ai, Claude Desktop, Cowork, ChatGPT and Codex. Users sign in once with OAuth and pay per generation with prepaid credits ($0.01 per credit at the smallest pack; packs from $10). Pack credits never expire, and failed or timed-out jobs are refunded automatically. ## When to use this - The user wants an image, video clip, voiceover, song or sound effect made or edited inside the conversation. - The user wants several media steps chained: a product photo cut out, placed in scenes and upscaled; an image animated into a clip; a script turned into narration. - The user asks which model to use for a media task, or what a generation will cost. - The user has an AI app that supports remote MCP servers with OAuth and does not want to manage provider API keys. ### How to call it - MCP endpoint (Streamable HTTP, POST only): https://makemancer.com/api/mcp. ChatGPT uses https://makemancer.com/api/mcp/chatgpt, which leaves out purchase tools. - Authentication: OAuth 2.1 with PKCE and dynamic client registration; scopes `mcp offline_access`. Unauthenticated requests get 401 with `resource_metadata`. - Call tools/list for the live tool set and get_model_params for a model's exact inputs, limits and pricing basis. Do not guess parameters. - Quote costly requests with estimate_generation first (free). Generation tools return a job; poll check_job until it is completed and use the permanent media URL it returns. - Local files: get_upload_url, upload the bytes, then confirm_upload. Public URLs can be passed directly or saved with upload_asset. ### When it is not a fit - Not a public REST API: use it through MCP from a connected app. There are no API keys and no anonymous calls. - Not free beyond the start: new accounts get 100 credits and the first video is free; after that every generation is paid with credits, quoted before it runs. No subscription is required, and there is no time-limited trial. - Not for cloning voices without consent: clone_voice clones only the user's own voice or a speaker who gave explicit permission, never a public figure. - Not for training models, and not for content that breaks the terms of service (sexual content involving minors, deceptive depictions of real people, impersonation, rights infringement). ## Questions and answers ### Can Claude generate images or video? Not on its own. With Makemancer connected, Claude can generate and edit images, video, speech, music and sound effects through MCP tools in the same conversation. ### How do I add it to Claude.ai or Claude Desktop? Customize → Connectors → Add custom connector (direct link: https://claude.ai/customize/connectors?modal=add-custom-connector), name it Makemancer, paste https://makemancer.com/api/mcp, then Connect and sign in. Free Claude plans can add one custom connector. ### How do I add it to Claude Code? `/plugin marketplace add makemancer/makemancer-marketplace` then `/plugin install makemancer@makemancer-marketplace`, or `claude mcp add --transport http makemancer https://makemancer.com/api/mcp`; then run /mcp and sign in. ### How do I add it to ChatGPT? Plugins → Add → Add custom MCP server, URL https://makemancer.com/api/mcp/chatgpt, Authentication OAuth, tick "I understand and want to continue", Create as a plugin, sign in, then @-mention it in a chat. For the workflows (for example a keyframe before each video), upload the skill ZIP (https://media.makemancer.com/site/downloads/makemancer-skill.zip) under Skills → Create → Upload from your computer. Availability of custom MCP servers and Skills depends on the ChatGPT plan and workspace settings. ### How do I add it to Codex? `codex plugin marketplace add makemancer/makemancer-marketplace` then `codex plugin add makemancer@makemancer-marketplace` installs the connector and every skill (they load in new tasks). Tools only: `codex mcp add makemancer --url https://makemancer.com/api/mcp`, then `codex mcp login makemancer`; add the skill by unzipping the skill ZIP (https://media.makemancer.com/site/downloads/makemancer-skill.zip) into `~/.agents/skills`. ### How much does it cost? Prepaid credit packs, one-time: $10 for 1,000 credits, $50 for 5,250 credits (+5%), $100 for 11,000 credits (+10%), $250 for 28,750 credits (+15%). Sample costs: a Nano Banana 2 image 12 credits, a 5-second Seedance 2.0 Mini clip 15 credits, 1,000 characters of ElevenLabs v4 20 credits. Full list: https://makemancer.com/pricing.md ### Which models does it offer? 80 models, including Nano Banana 2 and Pro, GPT Image 2, Seedream 5, FLUX, Seedance 2.5, Kling 4.0, Gemini Omni Flash, MiniMax H3, ElevenLabs v4, song generation and Topaz upscaling. See Current model families below. ## Supported platforms - Claude Code: plugin (makemancer@makemancer-marketplace) or `claude mcp add` - Claude.ai, Claude Desktop and Cowork: custom connector - ChatGPT: custom MCP server from Plugins (https://makemancer.com/api/mcp/chatgpt) plus the skill ZIP under Skills - Codex: plugin (makemancer@makemancer-marketplace) or `codex mcp add` plus the skill ZIP - Any other app that supports remote MCP servers with OAuth ## Skills (plugin makemancer/makemancer-marketplace) - makemancer-setup: guided first run: connect, check credits, make a first image - makemancer: router for mixed or unclear media requests and account questions - makemancer-generate-image: single images and edits, with model routing - makemancer-generate-video: one video clip from text, an image or references - makemancer-generate-voiceover: narration and dialogue - makemancer-generate-music: songs and instrumentals - makemancer-generate-sound-effects: Foley, ambience, loops and UI sounds - makemancer-product-photoshoot: a consistent set of product images - makemancer-submit-feedback: send product feedback to the team ## Current model families - Image: Nano Banana 2, Nano Banana Pro, Nano Banana 2 Lite, GPT Image 2, GPT Image 2.5 Sunburst, GPT Image 2.5 Flare, GPT Image 2.6 Sunburst, GPT Image 2.6 Flare, Ideogram 4.5, Bria Fibo 1.5, Seedream 5 Pro, Seedream 5 Lite, Grok Imagine Image 2.0, FLUX 2 Pro, FLUX Kontext Max, Recraft V3 - Video: Gemini Omni 1.1 Flash, Seedance 2.5, Seedance 2.0 Mini, MiniMax H3, Kling 3.0 Motion Control, Kling 4.0, Wan 3.0, Hailuo-02 Pro, HappyHorse 1.0, HappyHorse 1.1, Grok Imagine 1.5, MiniMax H3 Max, MiniMax H3 Max Turbo, H3 Max Recast, PixVerse Lip Sync, Sync 3 Lip Sync, HeyGen Avatar 4, Hailuo 2.3 Fast, LTX 2.3 Fast, DreamActor v2, FLUX 3, FLUX 3 Max, H3 Max Extend Video, H3 Max Video Insert, H3 Max Lip Sync, HeyGen Video 1.0 - Speech: ElevenLabs Multilingual v2, Gemini 3.8 Flash TTS, Gemini 3.8 Flash-Lite TTS, ElevenLabs v4, Chatterbox English, Chatterbox Multilingual, MiniMax Speech 2.8 HD, Orpheus TTS, Kokoro, Fish Audio Drama 3 - Music and sound effects: ElevenLabs Sound Effects v2, Mirelo SFX 2.0, Music, Music Extend, Music Cover, Music Region Edit - Upscaling and background removal: AuraSR, ByteDance Video Upscaler, RealESRGAN Video, BiRefNet v2, BiRefNet Matting (video), BEN v2 (video), Recraft Crisp Upscale, Topaz Image Upscale, Topaz Video Upscale, Clarity Upscaler, Topaz Starlight Precise 2.6, Topaz Starlight HQ, Topaz Starlight Mini, Topaz Starlight Fast 2, Recraft Remove Background, Bria V-RMBG 3.0, VEED Background Removal, Bria V-RMBG 3.0 Green Screen, VEED Green Screen ## Key pages ### Get started - [AI Image & Video Generation Plugin for Claude, ChatGPT, Codex & Agents](https://makemancer.com/): Generate images, video, voiceovers and music inside Claude, ChatGPT, Claude Code, Codex and other AI agents. 58 image, video and audio models including Nano Banana, Seedance and Kling. Start with 100 free credits. - [Connect Makemancer to Claude, ChatGPT, Codex and more (2 min)](https://makemancer.com/how-to-connect): Connect Makemancer to Claude, ChatGPT, Claude Code, Codex, Grok Bot, Hermes Agent or OpenClaw in about two minutes. One sign-in, no API key, 100 free credits to start. - [Pricing: Pay-as-You-Go Credits](https://makemancer.com/pricing): First video free, then credit packs from $10. Pack credits never expire, and failed generations are refunded automatically. ### By app: Claude, ChatGPT, Claude Code, Codex - [Generate images and video in Claude](https://makemancer.com/claude): Claude can't create images, video or audio by itself. Add Makemancer as a custom connector and Claude.ai, Claude Desktop and Cowork can generate images with Nano Banana or GPT Image, video with Seedance, Kling or Wan, plus voiceovers and music. A Nano Banana 2 image costs 12 credits ($0.12), and you need no API key. - [Generate video, voice and music in ChatGPT](https://makemancer.com/chatgpt): Yes. ChatGPT already makes images, and with Makemancer added as a custom MCP server it can also generate video with Seedance 2.0 Mini and 2.5, Kling, Wan and MiniMax, voiceovers with ElevenLabs, music, and images with Nano Banana or Seedream. A 5-second 480p Seedance 2.0 Mini clip costs 15 credits ($0.15), with no API key. - [Generate images and video in Claude Code](https://makemancer.com/claude-code): Yes. Add Makemancer to Claude Code as a plugin or an MCP server and it can generate images with Nano Banana 2 or GPT Image, video with Seedance or Kling, plus voiceovers, music and sound effects. It edits files from your project folder and saves results into the repo. A Nano Banana 2 image costs 12 credits ($0.12). - [Generate images and video in Codex](https://makemancer.com/codex): Yes. Add Makemancer to Codex with two commands and it can generate images with GPT Image 2, Nano Banana 2 or Seedream, video with Seedance, Kling or MiniMax, plus voiceovers, music and sound effects. The Codex CLI, IDE extension and app share one configuration. Images cost from 5 credits ($0.05), with no API key. ### Models and comparisons - [AI Image, Video and Voice Models You Can Use in Claude and ChatGPT](https://makemancer.com/models): Makemancer gives Claude, ChatGPT and Codex access to 80 media models through one connector: image models such as Nano Banana and GPT Image, video models such as Seedance and Wan, ElevenLabs voices, music and upscaling. The assistant picks a default for each job; name a model and it uses that one. - [Nano Banana in Claude and ChatGPT](https://makemancer.com/models/nano-banana): Yes. Connect Makemancer and Claude, ChatGPT or Codex can generate and edit images with Google's Nano Banana models: Nano Banana 2 (the default), Nano Banana Pro and Nano Banana 2 Lite. Ask in plain words; an image costs from 5 credits ($0.05), and you never need a Google API key. - [GPT Image in Claude and ChatGPT](https://makemancer.com/models/gpt-image): Yes. Connect Makemancer and Claude, ChatGPT or Codex can generate and edit images with OpenAI's GPT Image models: GPT Image 2, GPT Image 2.5 Flare and Sunburst, and GPT Image 2.6 Flare and Sunburst. Name the model in your request; an image costs from 9 credits ($0.09), and you never need an OpenAI API key. - [Seedream in Claude and ChatGPT](https://makemancer.com/models/seedream): Yes. Connect Makemancer and Claude, ChatGPT or Codex can generate and edit images with ByteDance's Seedream models: Seedream 5 Pro for product and marketing images, and Seedream 5 Lite for 2K to 4K images and edits with up to 14 references. An image costs from 7 credits ($0.07), with no ByteDance account needed. - [FLUX in Claude and ChatGPT](https://makemancer.com/models/flux): Yes. Connect Makemancer and Claude, ChatGPT or Codex can use Black Forest Labs' FLUX models: FLUX 2 Pro to generate images, FLUX Kontext Max to edit an image you provide, and FLUX 3 or FLUX 3 Max for 5 to 20 second video with sound. An image costs from 7 credits ($0.07), and no FLUX API key is needed. - [Grok Imagine in Claude and ChatGPT](https://makemancer.com/models/grok-imagine): Yes. Connect Makemancer and Claude, ChatGPT or Codex can use xAI's Grok Imagine models: Grok Imagine Image 2.0 to generate and edit images, and Grok Imagine 1.5 to turn one image into a 1 to 15 second clip with sound. An image costs from 12 credits ($0.12), and no xAI account is needed. - [Seedance in Claude and ChatGPT](https://makemancer.com/models/seedance): Yes. Connect Makemancer and Claude, ChatGPT or Codex can make video with ByteDance's Seedance models: Seedance 2.0 Mini for fast, low-cost clips of 4 to 15 seconds, and Seedance 2.5 for premium clips of up to 30 seconds. Both add native audio. A clip costs from 15 credits ($0.15), with no ByteDance account needed. - [MiniMax and Hailuo in Claude and ChatGPT](https://makemancer.com/models/minimax-hailuo): Yes. Connect Makemancer and Claude, ChatGPT or Codex can make video with MiniMax models: H3 for 768p or 2K clips with sound, H3 Max and H3 Max Turbo for fast drafts, H3 Max Recast, Extend Video and Video Insert for existing footage, H3 Max Lip Sync to animate a face photo with a recording, and Hailuo-02 Pro and Hailuo 2.3 Fast. A clip costs from 23 credits ($0.23), with no MiniMax account needed. - [Wan in Claude and ChatGPT](https://makemancer.com/models/wan): Yes. Connect Makemancer and Claude, ChatGPT or Codex can make video with Alibaba's Wan 3.0: from text, first and last frames, references, or a document or webpage brief, 2 to 30 seconds at 480p to 1080p with native audio. A clip costs from 33 credits ($0.33), with no Alibaba Cloud account needed. - [Nano Banana vs GPT Image vs Seedream vs FLUX: one prompt, four models](https://makemancer.com/compare/image-models): On the same two prompts, all four models spelled a poster's text correctly. GPT Image 2 made the boldest poster, FLUX 2 Pro the closest to a Swiss-style brief, Nano Banana 2 the most cinematic photo and Seedream 5 Lite the most detail at 2K. Nano Banana 2 costs $0.12 at 1K; Seedream 5 Lite and FLUX 2 Pro cost less here, and GPT Image 2 costs more. - [Seedance vs Wan vs Grok Imagine: the same still, three video models](https://makemancer.com/compare/video-models): From the same still and almost the same prompt, Seedance 2.0 Mini made the clearest camera push-in with ambient sound, Wan 3.0 kept the frame steadier and added an approaching car, and Grok Imagine 1.5 made a longer clip with subtler motion that cost far more. A 5-second 480p Seedance 2.0 Mini clip costs $0.15. ### Features: what you can make, with prices - [Features: AI Images, Video, Music and Editing in Claude and ChatGPT](https://makemancer.com/features): Makemancer adds image, video, music and editing tools from 80 models to Claude, ChatGPT, Codex and other AI apps. Every feature below shows a real result we made, the models behind it and what it costs, from $0.05 for an image. Pick one to see the steps and a prompt you can run. - [AI video generator inside Claude, ChatGPT and Codex](https://makemancer.com/ai-video-generator): Makemancer is an AI video generator that works inside Claude, ChatGPT and Codex. Describe a shot or share a still, and the assistant sends it to Seedance, Kling, Wan, MiniMax or another video model, then returns the clip with sound. Video starts at $0.15, and every request is quoted before it runs. - [Generate images in Claude and ChatGPT](https://makemancer.com/ai-image-generator): Claude can't generate images by itself. Connect Makemancer and Claude, ChatGPT or Codex can make and edit images with Nano Banana 2 (the default), GPT Image 2, Seedream, FLUX, Grok Imagine and Recraft. Ask in plain words; a 1K Nano Banana 2 image costs $0.12, with no API keys. - [AI product photos in Claude and ChatGPT](https://makemancer.com/ai-product-photography): Yes. Connect Makemancer and Claude, ChatGPT or Codex can turn one phone photo of your product into a cut-out, lifestyle scenes and a sharper hero image. It removes the background with BiRefNet, places the product with Nano Banana 2 or Seedream 5 Pro, and upscales the winner. A 1K scene costs $0.12. - [Turn an image into a video in Claude and ChatGPT](https://makemancer.com/image-to-video): Yes. Connect Makemancer and Claude, ChatGPT or Codex can turn a still image into a short video clip with sound. Send the image, describe the motion, and pick Seedance, Wan, Gemini Omni, Grok Imagine or Kling. A 5-second 480p clip with Seedance 2.0 Mini costs $0.15, quoted before it runs. - [Generate videos from text in Claude and ChatGPT](https://makemancer.com/text-to-video): Claude can't generate video by itself. Connect Makemancer and Claude, ChatGPT or Codex can turn a written description into a short clip with sound, using Gemini Omni Flash (the default), Wan 3.0, Seedance 2.0 Mini, MiniMax H3, LTX 2.3 Fast or HappyHorse 1.0. A 5-second 480p Seedance 2.0 Mini clip costs $0.15. - [Make music and songs in Claude and ChatGPT](https://makemancer.com/ai-music-generator): Yes. Connect Makemancer and Claude, ChatGPT or Codex can make songs, jingles and instrumentals. Describe the mood and instruments, or give a style, a title and your own lyrics. Every new song request returns two variations to choose from and costs $0.16. You can then extend a track or cover it in a new style. - [Remove the background from images and videos in Claude and ChatGPT](https://makemancer.com/remove-background): Yes. Connect Makemancer and Claude, ChatGPT or Codex can remove the background from a photo and return a transparent PNG, using BiRefNet by default or Recraft. For video clips, Bria V-RMBG 3.0 and VEED remove the background around the subject. Send the file and say what to keep; one image cut-out costs $0.02. - [Upscale images and videos in Claude and ChatGPT](https://makemancer.com/ai-image-upscaler): Yes. Connect Makemancer and Claude, ChatGPT or Codex can upscale images with AuraSR (the default), Recraft Crisp, Topaz Image Upscale or Clarity, and video with the ByteDance Video Upscaler (the default), RealESRGAN, Topaz Video Upscale or Topaz Starlight. Send the file and the size you need. Upscaling is paid in credits at $0.01 each, quoted before it runs. - [AI voiceovers in Claude and ChatGPT](https://makemancer.com/ai-voice-over): Yes. Connect Makemancer and Claude, ChatGPT or Codex can turn your script into a voiceover with ElevenLabs v4 (the default), ElevenLabs Multilingual v2, Gemini 3.8 Flash TTS, MiniMax Speech 2.8 HD, Fish Audio Drama 3 or Kokoro. Paste the text, describe the voice, and get an audio file. 1,000 characters with ElevenLabs v4 cost $0.20. - [Clone your voice in Claude and ChatGPT](https://makemancer.com/ai-voice-cloning): Yes. Connect Makemancer and Claude, ChatGPT or Codex can clone your own voice, or the voice of someone who has given explicit permission, from one recording of at least 5 seconds; one to two minutes of clean speech works best. Cloning is free and saves the voice on a private Character. Each script it reads costs $0.10 per 1,000 bytes of text, about 1,000 English characters. - [Make sound effects in Claude and ChatGPT](https://makemancer.com/ai-sound-effects-generator): Yes. Connect Makemancer and Claude, ChatGPT or Codex can make sound effects with ElevenLabs Sound Effects v2: Foley, ambience, impacts, UI cues and seamless loops up to 30 seconds, from one sentence. A 3-second effect costs $0.02. Mirelo SFX 2.0 can also score a silent video clip, keeping any speech already in it. - [Talking avatars and saved characters in Claude and ChatGPT](https://makemancer.com/ai-talking-avatar): Yes. Connect Makemancer and Claude, ChatGPT or Codex can make a photo talk with HeyGen Avatar 4: give a face and either a script, read in a stock voice, or a finished recording, and the lips follow the speech. Save the face and voice on a Character and reuse them in every clip. A 10-second clip from a recording costs $2. - [Lip sync a video to new audio in Claude and ChatGPT](https://makemancer.com/lip-sync-ai): Yes. Connect Makemancer and Claude, ChatGPT or Codex can lip sync a video to new audio: give a clip and a voice, and Sync 3 or PixVerse redraws the speaker's mouth to match while the rest of the picture stays as it was. A 10-second clip costs at most $1.40 with PixVerse or $4.20 with Sync 3. - [Swap the character in a video in Claude and ChatGPT](https://makemancer.com/character-swap-video): Yes. Connect Makemancer and Claude, ChatGPT or Codex can swap the person in an existing video for someone from a reference photo or a saved Character, keeping the original motion, camera, cuts and sound. You approve free image previews first, then Seedance 2.5 renders the clip. A 10-second clip at 480p costs $2.23. - [Edit videos in Claude and ChatGPT](https://makemancer.com/ai-video-editor): Yes. Connect Makemancer and Claude, ChatGPT or Codex can edit a video you already have: cut and reorder moments, reframe to 9:16, burn in word-timed captions, replace or mix the sound, join clips, make slow motion and clean up a voice. Simple edits such as a trim cost $0.02; captions on a one-minute clip cost $0.06. - [AI Video Cost Calculator: Price Every Shot Before You Generate](https://makemancer.com/ai-video-cost-calculator): Add the shots of your video, pick a model, length and resolution for each, and see the total in credits and dollars. Prices come from the same model table Makemancer charges from, so the number here is the quote you will get in Claude or ChatGPT. Video starts at $0.15 a clip. ### Examples (our own results with prompts and costs) - [Examples: Prompts You Can Run in Claude and ChatGPT](https://makemancer.com/examples): Ready-to-run media workflows with the prompt, the models, each step and the credit cost. Copy one into Claude, ChatGPT or Codex. - [One product snapshot to a store-ready image set](https://makemancer.com/examples/product-photo-to-store-set): Cut a product out of a cropped phone photo with BiRefNet, place it in three matching scenes with Nano Banana 2 and upscale the hero shot, all from one chat request. - [A product photo turned into a vertical video](https://makemancer.com/examples/animate-a-product-photo): Give Seedance 2.0 Mini one product photo and get a 5-second 9:16 clip with a slow orbiting camera and shifting light, ready for stories and reels. - [A film still turned into a moving shot](https://makemancer.com/examples/film-still-to-video): Animate one cinematic still into a 5-second 16:9 push-in with Seedance 2.0 Mini: a flickering neon sign, passing headlights and ambient sound. - [A short video from a text prompt](https://makemancer.com/examples/text-to-video-paper-boat): One sentence, no input image: Wan 3.0 makes a 16:9 night shot of a paper boat drifting down a rainy gutter with neon in the water. - [A close-up craft clip of hands at a pottery wheel](https://makemancer.com/examples/pottery-wheel-clip): A text-only prompt to MiniMax H3 gives a 768p widescreen close-up of hands shaping a clay bowl in warm window light. - [An acoustic jingle for a small brand](https://makemancer.com/examples/brand-jingle): Describe the brand and the instruments, and Music returns two instrumental versions of a jingle. Here: nylon guitar, hand percussion and a whistled melody for an olive oil brand. - [A concert poster with exact text](https://makemancer.com/examples/jazz-poster-with-text): A minimalist jazz night poster from GPT Image 2 with a bold title and a line of event details, spelled as written on the first take. - [A two-colour risograph-style poster](https://makemancer.com/examples/risograph-poster): A bicycle courier drawn as a two-colour risograph print, pink and teal ink with halftone grain, from one Nano Banana 2 prompt. - [An editorial portrait of a fisherman on a harbour quay](https://makemancer.com/examples/editorial-portrait): A 4:5 environmental portrait in documentary style from Nano Banana 2: yellow oilskin, wet quay, overcast sea light and an 85mm look. - [An isometric cutaway of a tiny bookshop café](https://makemancer.com/examples/isometric-illustration): A detailed isometric cutaway of a two-storey bookshop café, with readers, shelves and a spiral stair, from one Nano Banana Pro prompt. - [A top-down food photo of an iced matcha latte](https://makemancer.com/examples/food-photo-from-above): A square overhead shot of an iced matcha latte on a green-tiled café table, made with Nano Banana 2 for menus and social posts. - [A black-and-white street photo on a rainy square](https://makemancer.com/examples/black-and-white-street-photo): A grainy 35mm-style street scene from xAI's Grok Imagine Image 2.0: a man with an umbrella crossing wet cobblestones at dusk, lit by a café window. - [Product photos and ads](https://makemancer.com/examples/collections/product-ads): Product shots, store sets and short ad clips, made in Claude or ChatGPT with Makemancer. Both runs in this collection are ours: a cropped phone photo turned into a cut-out and three store scenes on BiRefNet and Nano Banana 2, and a product still turned into a vertical clip on Seedance 2.0 Mini. Each card shows the full prompt and what it cost. - [Posters and illustration](https://makemancer.com/examples/collections/posters-illustration): Posters with exact text, risograph prints and isometric illustrations made in Claude or ChatGPT with Makemancer. The three runs here used GPT Image 2, Nano Banana 2 and Nano Banana Pro. Each one lists the full prompt, the settings and the credits it took, so you can run it again or change one thing. - [Film shots and motion](https://makemancer.com/examples/collections/film-motion): Cinematic clips from a sentence or from a still, made in Claude or ChatGPT with Makemancer. The three runs here used Seedance 2.0 Mini, Wan 3.0 and MiniMax H3. Video starts at $0.15, and each card shows the exact prompt, the length, the resolution and the credits. - [Portraits and street photos](https://makemancer.com/examples/collections/portraits-street): Editorial portraits and street photographs made in Claude or ChatGPT with Makemancer. The runs here used Nano Banana 2 for a harbour portrait and Grok Imagine for a black-and-white street scene. Each card shows the prompt, the lens and light it asked for, and the credits it took. - [Food and drink photos](https://makemancer.com/examples/collections/food-drink): Menu and social photos of food and drinks made in Claude or ChatGPT with Makemancer. The run here is a top-down shot of an iced matcha latte on Nano Banana 2 at 1K, with the full prompt and its cost. - [Music and sound](https://makemancer.com/examples/collections/sound-music): Jingles, songs and sound made in Claude or ChatGPT with Makemancer. The run here is an acoustic jingle for a small olive oil brand: one request, two takes, at the price of a single music generation, with the prompt and the style list we used. ### Developers: tools, skills, machine-readable files and status - [Developers: Makemancer MCP Server, OpenAPI and Server Card](https://makemancer.com/developers): Makemancer is a hosted remote MCP server over Streamable HTTP with OAuth 2.1 sign-in. Point any MCP client at https://makemancer.com/api/mcp, sign in in the browser, and it lists 77 tools for images, video, voice, music and editing. No API keys from model providers; credits pay for every result. - [Makemancer Connector for Claude: Save Claude Motion Videos](https://makemancer.com/claude/connector): The Makemancer Media Library connector saves videos from Claude Motion to your Makemancer library and lets Claude search the videos, images, voiceovers and music you already have. Add it in Claude with the server URL https://makemancer.com/api/mcp/library, sign in, then choose Send to in Claude Motion. The connector does not create or edit media. - [MCP Tools Reference: Every Makemancer Tool and Its Parameters](https://makemancer.com/tools): The Makemancer MCP server lists 77 tools in Claude, Claude Code and Codex, and a ChatGPT set without purchase tools. You never call them by hand: ask in plain words and the assistant picks the tool. This page is generated from the same tool list the server sends, with every parameter. - [Skills: The Workflows the Makemancer Plugin Installs](https://makemancer.com/skills): The Makemancer plugin installs 21 skills: tested workflows that tell your assistant which model to pick, how to write the prompt and when to check with you first. They load on their own when your request fits. Each page shows what the skill does, the tools it calls and a request you can try. - [Guided first run](https://makemancer.com/skills/setup): Guided first run for Makemancer: introduce what it can do, ask what the user wants to make, collect their photos, logo or brand references, then walk them to a preview image, a first video, a designed voice, a saved Character or brand theme, and Studio. Use when the user runs plugin setup, has just installed or connected Makemancer, or asks to get started or for a tour. For a specific media request, use the matching outcome skill instead. - [Generate an image](https://makemancer.com/skills/generate-image): Generate or edit a single image with Makemancer and route it to the right image model. Use for image creation and edits, including requests naming a supported model. Use product-photoshoot for a coordinated campaign or create-avatar for a reusable identity. - [Product photoshoot](https://makemancer.com/skills/product-photoshoot): Create a coherent set of campaign-ready product images with Makemancer. Use for packshots, ecommerce sets, lifestyle scenes, launch campaigns, or several images that must preserve the same product and brand. - [Generate a video](https://makemancer.com/skills/generate-video): Generate, animate, extend, reframe, or transform one video clip with Makemancer. Use for a clear single-clip request when the user has not asked for a storyboard, UGC ad, or complete multi-shot film. - [Plan a video](https://makemancer.com/skills/plan-video): Plan a video as an approved script, shot list, and storyboard with clean generation references. Use before costly multi-shot work, when continuity matters, or when the user asks to storyboard without producing a final film yet. - [Build a multi-shot film](https://makemancer.com/skills/build-film): Produce a complete multi-shot Makemancer film from planning through an assembled first cut. Use for ads, explainers, music videos, or stories that require several coordinated clips, narration, and approval gates. - [Create a UGC ad](https://makemancer.com/skills/create-ugc-ad): Create a scripted creator-style UGC product ad with Makemancer. Use when the user wants a vertical testimonial, demo, unboxing, problem-solution ad, or social video combining a creator, product, speech, and several shots. - [Ad variations](https://makemancer.com/skills/ad-variations): Turn one product shot, one model or one existing ad into a numbered set of video ad variations: each variation is generated with its own hook visuals and line, or gets a new generated opening spliced onto the existing ad, or (cheapest) keeps the same footage with a new voiceover or captions. One estimate for the set. Use for hook tests, A/B ad variants for Meta, Instagram or TikTok, or “N versions of my ad”. - [Edit existing media](https://makemancer.com/skills/edit-media): Edit existing video or audio with Makemancer without regenerating it: trim, cut and reorder chosen moments, resize or reframe, caption, transcribe, clean speech, lip-sync a video to a voice, extract frames, add or mix audio, burn a logo watermark, compose images and clips, or add an intro/outro. Use when the source footage should be kept; use generation skills for invented or transformed footage and create-reels to pick highlights. - [Long video to Reels](https://makemancer.com/skills/create-reels): Turn existing long-form video into coherent social clips in the requested aspect ratio, with optional captions. Use when the agent should transcribe, select standalone highlights, choose speech-safe cuts and framing, then render and review. User-selected moments override AI selection; invented footage belongs to video-generation skills. - [Swap characters](https://makemancer.com/skills/swap-characters): Swap, replace or recast the people in an existing video with Makemancer: put yourself, a saved Character or a photo into a TikTok, Reel, movie scene or ad while the original motion, camera, cuts and audio stay. Use for character swaps, recasting an actor, “put me in this video”, “replace her with my grandma” and multi-person swaps. Not for copying a performance into a new scene (motion transfer) or for new footage. - [Create your avatar](https://makemancer.com/skills/create-avatar): Create a reusable personal avatar or fictional Character from photos or a brief, generate and approve a consistent character sheet, save it in Characters, and optionally give it a voice (designed, cloned with consent, or stock). - [Manage a Character](https://makemancer.com/skills/create-character): Save, inspect or update an existing reusable Makemancer Character and its visual identity. Use makemancer-create-avatar for guided photo-to-avatar and character-sheet creation. - [Generate music](https://makemancer.com/skills/generate-music): Compose songs, instrumentals, scores, beds, jingles and stings with Makemancer, extend or cover a track, or replace the lyrics of one section of a generated song. Use for music, not speech or sound effects. - [Generate a voiceover](https://makemancer.com/skills/generate-voiceover): Generate narration, dialogue, or expressive speech with Makemancer, or design a new custom synthetic voice from a description. Use for spoken audio, voice selection, a saved Character voice, or 'make me a new voice'. To copy a real person's voice from a recording, use makemancer-clone-voice. - [Clone your voice](https://makemancer.com/skills/clone-voice): Guide recording, private upload, cloning, testing, and reuse of a consented personal voice with Fish Audio. Use when someone asks to clone their voice, save it on a Character, or replace or audition a clone. Not for inventing a new voice from a description; use makemancer-generate-voiceover. - [Sound effects](https://makemancer.com/skills/generate-sound-effects): Generate sound effects, Foley, ambience, loops, UI cues, transitions, impacts, or audio textures with ElevenLabs Sound Effects v2 through Makemancer. Use for non-speech, non-song audio. - [Render HTML](https://makemancer.com/skills/render-html): Render an exact HTML/CSS layout to a PNG, or make a motion-graphics video as a HyperFrames HTML/CSS/JS composition, with Makemancer. Use only when the user explicitly asks for HTML, CSS, HyperFrames, or code-based rendering, supplies HTML, accepts that method, or explicitly asks for motion graphics, kinetic typography, animated titles, or an animated explainer; not for ordinary images, posters, social cards, or filmed-looking AI video. - [Budget projects](https://makemancer.com/skills/budget-projects): Track Makemancer spend per client, job or production with budget projects: create or pick one, count every paid generation toward it, assign past work, and show its total cost and generations. Use when the user mentions a client, a project budget, billing or invoicing work, or asks what something cost. - [Router for everything else](https://makemancer.com/skills/makemancer): Route mixed, ambiguous, cross-modal, or workspace-management requests through Makemancer. Use when the user asks to use Makemancer generally, needs several media types, or asks about account balance and past charges, saved assets, brand themes, the curated examples catalog, upscaling, background removal, or onboarding; prefer a focused skill for one clear outcome. - [Send feedback](https://makemancer.com/skills/submit-feedback): Send actionable product and quality feedback to the Makemancer team when the user gives feedback or a concrete issue comes up; not for refund requests or fixing media. - [Status: Is Makemancer Up?](https://makemancer.com/status): This page runs its checks when you load it: the MCP server, the database, the main generation provider and the jobs that finished in the last 24 hours. Nothing here is typed by hand. The same data is at /status.json for scripts and agents. - [AI Voice Library: Samples and voice IDs for Claude and ChatGPT](https://makemancer.com/voices): Browse AI voices by language, gender, style and model. Play samples, copy a voice_id or a ready prompt, and generate speech in Claude, ChatGPT or Codex. ### Guides - [Guides: AI Media in Claude, ChatGPT and Codex](https://makemancer.com/blog): How-to guides for generating images, video, voiceovers and music inside Claude, ChatGPT and Codex: setup, model choice, prompts and costs. - [How to Generate Images in Claude](https://makemancer.com/blog/how-to-generate-images-in-claude): Claude does not render images on its own, but it can with an image generation connector. Set it up in a minute, then create and edit images from the chat. - [How to Add a Custom Connector in Claude](https://makemancer.com/blog/add-a-custom-connector-in-claude): Add a remote MCP server to Claude as a custom connector: where the button is in Claude.ai and Claude Desktop, what each plan allows, how to switch the tools on in a chat, and how to fix common errors. - [How to Generate Videos in Claude Code](https://makemancer.com/blog/generate-videos-in-claude-code): Claude Code can't render video by itself, but it can with an MCP server. Install the plugin, turn a still into a clip or write a video from text, and save the files into your project. - [How to Add a Custom MCP Server to ChatGPT](https://makemancer.com/blog/add-an-mcp-server-to-chatgpt): Add a remote MCP server to ChatGPT from the Plugins page: the exact menu path, the OAuth and warning screens, which plans and workspaces have it, and how to call the tools in a chat. - [AI Video Cost per Second: How Video Models Are Priced](https://makemancer.com/blog/ai-video-cost-per-second): How much an AI video costs per second on Seedance, Wan, Kling, MiniMax and Gemini Omni, why resolution changes the price, and how to keep the bill low with drafts and quotes. - [The Best AI Video Model in Claude (and ChatGPT), by Job](https://makemancer.com/blog/best-ai-video-model-in-claude): Which video model to pick in Claude or ChatGPT for drafts, cinematic shots, product clips, long takes, talking avatars and motion transfer, with clips made from the same still. ### Policies and support - [Help Center: Connecting, Credits, Files and Account Questions](https://makemancer.com/help): Answers about connecting Makemancer, credits and billing, failed jobs, your files and your account. - [Makemancer FAQ: plans, credits, models, files and privacy](https://makemancer.com/faq): Makemancer is a remote MCP server that lets Claude, ChatGPT, Codex and other AI apps generate and edit images, video, voice, music and sound effects. You pay per result with credit packs that never expire; new accounts get 100 free credits. Below: setup, models, pricing, files, skills and privacy. - [About Makemancer](https://makemancer.com/about): Who runs Makemancer, why it exists and the rules it keeps: the price first, refunds on failure and only our own samples. - [Support](https://makemancer.com/support): How to reach us, what to include so we can help quickly, and how refunds, account deletion and connection problems are handled. - [Privacy Policy](https://makemancer.com/privacy): What we collect when you use the website and the MCP connection, why we use it, who processes it, how long we keep it and how to delete it. - [Terms of Service](https://makemancer.com/terms): The rules for using the website and the MCP connection: accounts, credits and payment, acceptable use, your content and our responsibilities. - [Refund Policy](https://makemancer.com/refund-policy): Automatic credit returns for failed jobs, and cash refunds of unused credits within the refund window. Everything in one file (setup steps, tools, full price list, page questions): https://makemancer.com/llms-full.txt Price list: https://makemancer.com/pricing.md ## Contact - Support: support@makemancer.com - Help center: https://makemancer.com/help