canonical: https://jentic.com/apis/contentmaschine.ai/contentmaschine # contentmaschine.ai API The ContentMaschine API generates and edits images, videos, audio, and text from one media endpoint set. It generates images and produces variations, fusions, upscales, background removals, and masked region edits, generates and merges videos, transcribes audio, and runs text tools. Long-running operations return a job that is polled for status, and generated files are served through short-lived signed links. Authentication uses a bearer API key with an sk-cm- prefix or an OAuth2 access token scoped per media type. ## For AI agents Generate and edit images, videos, audio, and text, poll long-running generation jobs, and fetch results through short-lived signed links with the ContentMaschine API. ## Scope Does not run a persistent media CDN beyond short-lived links, and does not handle live streaming. Use for AI generation and editing of images, video, audio, and text only. ## Capabilities - Generate images and produce variations, fusions, and upscales - Remove backgrounds and edit masked regions of an image - Generate videos and merge two videos together - Transcribe an audio file into text - Run text generation tools - Poll job status and fetch short-lived file links ## Use cases ### Agent-Generated Visual Assets An AI agent connected through Jentic can produce finished imagery without a person in the loop: it submits an image generation request, polls the job until it completes, and fetches a short-lived link to the result. The async job model lets the agent start a render and check back rather than holding a request open. Example prompt: Generate an image from a prompt, poll the job until it finishes, and fetch a short-lived link to the result ### Image Post-Processing Generated images often need cleanup before use. ContentMaschine upscales an image, removes its background, and edits a masked region, so an agent can take a raw render and turn it into a product-ready shot in a single pipeline of calls. Example prompt: Upscale a generated image and remove its background for a product shot ### Video Creation Short video assets can be assembled programmatically. ContentMaschine generates a video from a prompt and merges two videos the caller owns, so an agent can render clips and concatenate them into one deliverable. Example prompt: Generate two short video clips and merge them into one ### Audio Transcription Spoken content becomes searchable once transcribed. ContentMaschine transcribes an audio file the caller owns and returns the transcript, so an agent can turn a recording into text it can summarize or index. Example prompt: Transcribe an uploaded audio file and read the resulting transcript ## Key endpoints | Method | Path | Description | | --- | --- | --- | | POST | `/v1/images/generate` | Generate an image | | POST | `/v1/images/upscale` | Upscale an image | | POST | `/v1/images/remove-background` | Remove an image background | | POST | `/v1/videos/generate` | Generate a video | | POST | `/v1/audio/transcribe` | Transcribe an audio file | | POST | `/v1/text/generate` | Run a text generation tool | | GET | `/v1/jobs/{id}` | Poll job status | ## Key resources - **Images** — Generate, vary, fuse, upscale, describe, region-edit, and remove backgrounds - **Videos** — Generate videos and merge two videos together - **Audio and Text** — Transcribe audio and run text generation tools - **Files and Jobs** — Poll job status and fetch short-lived links to generated files ## 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: 49 / 100 - Developer Experience & Jentic Compatibility: 70 / 100 - AI-Readiness & Agent Experience: 53 / 100 - Agent Usability: 93 / 100 - Security: 75 / 100 - AI Discoverability: 67 / 100 - **View full report:** https://jentic.com/apis/contentmaschine.ai/contentmaschine/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 ContentMaschine by hand means handling its bearer sk-cm- key or an OAuth2 token with per-media-type scopes, and polling a job for every async image or video render. Through Jentic you install once, import ContentMaschine from the API Directory, store the credential once, and your agent calls it. - **Permission scoping:** ContentMaschine groups its operations by media type (images, videos, audio, text) and takes inputs in the request body rather than a resource in the URL path, so a rule bounds which operations your agent may call. Limit it to the operations it needs, such as image generation and upscaling, and leave video, audio, and file-deletion operations out unless you add them. - **Credential handling:** Your ContentMaschine key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context. - **Discovery method:** Agents search Jentic by intent such as 'generate an image' or 'transcribe audio', and Jentic returns the matching ContentMaschine operation with its input schema so the agent calls the right endpoint without browsing the reference docs. ## Related APIs - **Stability AI** — Stability AI generates and edits images through its own model API. - **Replicate** — Replicate runs many community image, video, and audio models behind one API. - **Leonardo.Ai** — Leonardo.Ai focuses on image generation and upscaling for creative work. - **ElevenLabs** — ElevenLabs generates speech and voice audio that pairs with generated video. ## FAQ ### What authentication does the ContentMaschine API use? The ContentMaschine API authenticates with a bearer API key (keys use an sk-cm- prefix) or an OAuth2 access token whose scopes are granted per media type, such as images:write or videos:read, per its OpenAPI spec. When you call it through Jentic, that credential is stored once by your own Jentic One instance and injected at execution time, so it never reaches the agent's prompt or logs. ### Can I edit an image with the ContentMaschine API, not just generate one? Yes. Beyond image generation, the API upscales an image, removes its background, edits a masked region, and creates variations and fusions, so an agent can run a full edit pipeline on an image it generated or uploaded. ### What are the rate limits for the ContentMaschine API? The OpenAPI spec does not define numeric rate limits for the ContentMaschine API. Check the ContentMaschine documentation at https://contentmaschine.ai for the current request limits that apply to your key. ### Can I limit what my agent is allowed to do with the ContentMaschine API? Yes. ContentMaschine groups operations by media type and takes inputs in the request body, so a rule bounds which operations the agent may call. Write a rule that allows only the image generation and upscale operations, so the agent can create and enlarge images but cannot generate video, transcribe audio, or delete files, and every call it makes is logged. ### How do I generate an image with the ContentMaschine API through Jentic? Search Jentic with an intent like 'generate an image from a prompt', and Jentic returns the image generation operation at `/v1/images/generate` with its input schema so your agent submits the prompt and then polls the job for the result. To run it on your own infrastructure, install Jentic One from its GitHub repo. ### Is there a ContentMaschine MCP server? You don't need an MCP server to give your agent ContentMaschine. Jentic connects it directly from the API Directory: import the API, store your key once, and your agent calls the image, video, audio, and text operations on demand.