canonical: https://jentic.com/apis/jabbertoon.com/jabbertoon # Jabbertoon tools for AI assistants and developers The Jabbertoon API gives an assistant the tools to write talking cartoons in Jabbertoon's block language over plain HTTP, with no key and no account. It returns guide topics such as cartoon, text, moves, and limits as Markdown, lists the six ready-made characters with their voices, the six art styles and three body shapes, and the ready-made moves a character can do, and returns any one move's block program. A validate tool checks a cartoon, scene, move, pack, or character with the studio's own checks and can return a repaired program, and a share tool turns the result into a jabbertoon.com link that opens it in the studio or block editor. Rendering the video happens on your own computer with the jabbertoon tool, not through this API. ## For AI agents Read Jabbertoon's cartoon-writing guide, look up characters, looks, and moves, validate and auto-repair a cartoon program, and turn it into a shareable jabbertoon.com studio link. ## Scope Does not render video, host finished cartoons, or generate images from prompts. Use for writing, validating, and sharing Jabbertoon cartoon programs only. ## Capabilities - Read one topic of the cartoon-writing guide, such as start, cartoon, moves, voices, or limits, as Markdown with GET `/api/get_guide` - List the six ready-made characters (person, kid, dog, cat, bird, monster), their colour slots, and voices with GET `/api/list_characters` - List art styles like crayon and storybook and body shapes like bighead with GET `/api/list_looks` - Search ready-made moves by word, so q 'dance' finds Groove, with GET `/api/list_moves`, and fetch one move's block program with GET `/api/get_move` - Validate a cartoon, program, pack, or character with POST `/api/validate`, getting errors with did_you_mean hints and an RFC 6902 patch, plus repaired output when repair is true - Turn a cartoon, move, or character into a jabbertoon.com studio link with POST `/api/share_link`, with nothing uploaded or kept - Report a wrong answer or a validator mistake to the Jabbertoon team with POST `/api/report_problem` ## Use cases ### Cartoon-writing assistant through Jentic An assistant asked for a short cartoon can write it end to end. Through Jentic it finds each Jabbertoon tool by intent: it reads GET `/api/get_guide` with topic start, casts characters from GET `/api/list_characters`, picks moves from GET `/api/list_moves`, checks the program with POST `/api/validate`, and returns a studio link from POST `/api/share_link.` No key is involved at any step. Example prompt: Call GET `/api/get_guide` with topic 'cartoon', write a two-character program for a dog and a cat, call POST `/api/validate` with that cartoon and repair true, then call POST `/api/share_link` with the repaired program ### Validation and auto-repair before sharing A cartoon written by a model often has small mistakes: an unknown op, a character off stage, a line cut off. POST `/api/validate` returns errors and warnings, each with code, where, says, fix, and url, plus did_you_mean and an RFC 6902 patch when the fix is certain, along with a summary of who is where and says what when. With repair set to true it also returns the program with every certain patch applied. Example prompt: Call POST `/api/validate` with the cartoon object and repair true, then report each remaining error's code and fix ### Building custom moves from ready-made ones To animate something the library lacks, start from the closest ready-made move. GET `/api/get_move` returns a move's block program as JSON and as screenplay text, by id like c4c:beh:wave_hello, short name, or page slug. Change it, validate it with POST `/api/validate` as a program, then open it in the block editor with POST `/api/share_link.` Example prompt: Call GET `/api/get_move` with move 'wave_hello', change the program so the character hops after waving, validate it via POST `/api/validate` with program set to the result, then share it via POST `/api/share_link` ## Key endpoints | Method | Path | Description | | --- | --- | --- | | GET | `/api/get_guide` | Read the cartoon-writing guide | | GET | `/api/list_characters` | List characters and voices | | GET | `/api/list_moves` | List ready-made moves | | GET | `/api/get_move` | Get one move's program | | GET | `/api/list_looks` | List art styles and body shapes | | POST | `/api/validate` | Validate a cartoon, move, pack, or character | | POST | `/api/share_link` | Make a jabbertoon.com link | ## Key resources - **Guide** — Markdown topics covering the cartoon program, screenplay text, moves, characters, looks, voices, places, errors, and limits - **Characters and looks** — Six ready-made characters with voices, six art styles, and three body shapes - **Moves** — Ready-made moves with their block programs, lengths, and settings - **Validation** — Errors, warnings, viewer-visible issues, and repaired programs - **Share links** — jabbertoon.com links that open a cartoon, move, or character with nothing uploaded ## AI readiness This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use. - **Score:** 64 / 100 - **Maturity:** AI-Aware - **Dimensions:** - Foundational Compliance: 48 / 100 - Developer Experience & Jentic Compatibility: 69 / 100 - AI-Readiness & Agent Experience: 51 / 100 - Agent Usability: 94 / 100 - Security: 100 / 100 - AI Discoverability: 64 / 100 - **View full report:** https://jentic.com/apis/jabbertoon.com/jabbertoon/scorecard - **How the score is calculated:** https://docs.jentic.com/reference/api-readiness-framework/overview/ - **More about the dimensions:** https://docs.jentic.com/reference/api-readiness-framework/specification/#dimensional-model-overview ### Score it yourself Every API in the directory is allowlisted, so you can re-score it with no key required. - **Score your own API:** https://jentic.com/scorecard.md - **Scoring CLI agent skill:** https://github.com/jentic/jentic-api-scorecard/blob/main/skills/jentic-api-scorecard/SKILL.md ```sh npx @jentic/api-scorecard-cli score ``` ## Why Jentic - **Setup:** Wiring Jabbertoon by hand means learning its paired GET and POST tool routes, its guide topics, and its error shape with RFC 6902 patches. Through Jentic you install once, import the Jabbertoon API from the API Directory, and your agent calls it with no credential to manage. - **Permission scoping:** Jabbertoon takes its arguments as query parameters or a JSON body rather than path ids, so rules bound which tools your agent may call, not which cartoon it works on. You choose the operations it may call, so the one tool that keeps what it is sent, report_problem, is not included unless you add it. - **Credential handling:** The Jabbertoon API needs no key or account, so there is nothing to store. For any API you add that does use a key, your own Jentic One instance keeps it encrypted and injects it at execution time, out of the agent's prompt, logs, and context. - **Discovery method:** Agents search Jentic by intent such as 'check a Jabbertoon cartoon' or 'find a cartoon move for waving', and Jentic returns the matching Jabbertoon operation with its input schema so the agent calls the right endpoint without browsing the reference docs. ## Related APIs - **Creatomate API** — Template-based video rendering in the cloud - **JSON2Video API** — Build videos from a JSON description - **ElevenLabs API** — Text-to-speech voices ## FAQ ### Is there a Jabbertoon MCP server? Yes - per its OpenAPI spec, Jabbertoon offers an MCP server with the same tools. You can also connect the Jabbertoon API directly through Jentic: your agent gets the full 13-endpoint surface from the spec without loading another server's tool definitions into its context, and your rules decide which operations the agent may call. ### Does the Jabbertoon API need authentication? No. Per its OpenAPI spec, the Jabbertoon API needs no key and no account, and it declares no security schemes. GET answers the read tools whose arguments are plain values, and POST accepts a JSON object of arguments for any tool. ### Does the Jabbertoon API render the cartoon video? No. Making the video is done on your own computer by the jabbertoon tool (preview and render_video). The HTTP API covers the guide, characters, looks, moves, validation, and share links; POST `/api/share_link` opens the cartoon in the jabbertoon.com studio. ### Can I limit what my agent is allowed to do with the Jabbertoon API? Yes. For example, write a rule that allows only the read tools and POST `/api/validate`, leaving out POST `/api/report_problem.` Your agent can then write and check cartoons but cannot file reports with the Jabbertoon team, and every call it makes is logged. ### What are the rate limits for the Jabbertoon API? The OpenAPI spec does not specify rate limits. The guide has a limits topic, readable with GET `/api/get_guide`, and https://jabbertoon.com/docs/language/ documents the block language. ### How do I validate a cartoon through Jentic? Search Jentic for 'check a Jabbertoon cartoon', load the validate operation, and call POST `/api/validate` with one of cartoon, program, pack, character, or file, adding repair true to get a patched program back. To run it on your own infrastructure, install Jentic One from its GitHub repo. ### Is anything I send to Jabbertoon stored? Per the spec, nothing sent to validate or share_link is stored or logged, and a share link carries everything after the # so nothing is uploaded. POST `/api/report_problem` is the exception: it saves the report for a person to read, so never put a cartoon, a name, or personal details in it.