canonical: https://jentic.com/apis/filmee.app/filmee

# Filmee App FilmeeAi API

The FilmeeAi API adds AI video editing to your own app. It edits a recorded talking-head video with explainer animation that matches what is said, burned-in subtitles, skin beautify, and background music, and it generates a narrated anime video from a text prompt. Every job is asynchronous: you create it, poll its status for free, then fetch the finished file. Credits are charged only on the first successful result call, and an account endpoint reports the balance, plan, and per-job prices.

## For AI agents

Edit recorded talking-head videos or generate narrated anime videos from text through an async job API. Poll status for free, fetch the finished file, and read credit balance and prices.

## Scope

Does not handle live streaming, video hosting, or voice cloning. Use for AI talking-head video editing and text-to-anime video generation only.

## Capabilities

- Edit a recorded talking-head video with explainer animation that matches the narration
- Add burned-in subtitles, skin beautify, and background music to a talking-head video
- Generate a narrated anime video from a text prompt
- Poll a video job's status for free until it finishes
- Fetch the finished video file, with credits charged only on the first successful result
- Check the account credit balance, plan, and per-job prices

## Use cases

### Agent video production through Jentic

An AI agent turns a recorded clip or a script into a finished video without a person babysitting the render. It submits a talking-head edit or an anime generation, polls the job for free until it reports done, then fetches the file, so a content pipeline can produce a video end to end and only spend credits when a result is actually delivered.

Example prompt: Submit a talking-head edit with subtitles enabled, poll the job until done, then fetch the finished file

### Explainer and social video from a recording

Creators record themselves and want a polished explainer without an editing suite. The talking-head endpoint adds animation that matches the speech, burned-in subtitles, skin beautify, and background music, so a workflow can take a raw recording and return a share-ready clip.

Example prompt: Edit a recorded talking-head video with subtitles and background music, then retrieve the result

### Narrated anime from text

Marketers and educators want short narrated animations without producing them by hand. The anime endpoint takes a text prompt and returns a narrated anime video, so a tool can script a storyline and get back a rendered clip to publish.

Example prompt: Generate a narrated anime video from a short text prompt and fetch the finished file once the job completes

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| GET | `/account` | Credit balance, plan, and prices |
| POST | `/talk-videos` | Edit a recorded talking-head video |
| POST | `/anime-videos` | Generate a narrated anime video from text |
| GET | `/videos/{id}` | Get a video job's status |
| POST | `/videos/{id}/result` | Fetch the finished file (charges credits on the first call) |

## Key resources

- **Talking-head videos** — Edit recorded talking-head videos with animation, subtitles, beautify, and music
- **Anime videos** — Generate narrated anime videos from a text prompt
- **Jobs** — Poll a video job's status and fetch its finished file
- **Account** — Read credit balance, plan, and per-job prices

## 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:** 44 / 100
- **Maturity:** Foundational
- **Dimensions:**
  - Foundational Compliance: 100 / 100
  - Developer Experience & Jentic Compatibility: 63 / 100
  - AI-Readiness & Agent Experience: 19 / 100
  - Agent Usability: 94 / 100
  - Security: 60 / 100
  - AI Discoverability: 70 / 100
- **View full report:** https://jentic.com/apis/filmee.app/filmee/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 <openapi-url>
```

## Why Jentic

- **Setup:** Wiring the FilmeeAi API by hand means handling its Bearer token, the asynchronous create-poll-result flow, and the credit accounting where only the first result call charges. Through Jentic you install once, import it from the API Directory, store the token once, and your agent calls it.
- **Permission scoping:** You choose which operations your agent may call, so it can create jobs and poll their status while the result operation, which charges credits, stays out unless you add it. The account read stays available so the agent can check the balance first.
- **Credential handling:** Your FilmeeAi token 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 a video from text' or 'edit a talking-head video', and Jentic returns the matching FilmeeAi operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **HeyGen** — HeyGen generates avatar and talking-head videos, an alternative to Filmee's talking-head editing.
- **Synthesia** — Synthesia produces AI avatar videos from scripts, an alternative generation backend to Filmee.
- **Shotstack** — Shotstack renders and edits video programmatically, useful for assembling clips Filmee produces.

## FAQ

### What authentication does the FilmeeAi API use?

It uses a Bearer token sent in the Authorization header, per its OpenAPI spec. The same credential reads your account balance and submits video jobs, and the account endpoint reports the plan and per-job prices so you know the cost before you render.

### How does the FilmeeAi API charge for a video?

Every job is asynchronous: you create it, poll its status for free, and then call the result endpoint to fetch the finished file. Credits are consumed only on the first successful result call, so polling status while a job renders costs nothing.

### What are the rate limits for the FilmeeAi API?

The OpenAPI spec does not state a request rate limit. Jobs are metered by credits rather than request count, so read the account endpoint for your balance and prices and check the Filmee documentation for any limits before batching renders.

### Is there a Filmee MCP server?

You don't need an MCP server to give your agent the FilmeeAi API. Jentic connects it directly from the API Directory: import it, store your token once, and your agent calls the edit, generate, status, and result operations on demand.

### Can I limit what my agent is allowed to do with the FilmeeAi API?

Yes. Write a rule that allows the create-job and status operations and the account read, and leave the result operation, which charges credits, off the list unless you add it, so an agent can prepare and track renders while you keep the paid step deliberate. Every call it makes is recorded in your Jentic One audit log.

### How do I generate a video with the FilmeeAi API through Jentic?

Search Jentic for 'generate a video from text', add the FilmeeAi API from the directory, and store your token once; your agent then submits the job, polls its status, and fetches the finished file. To run it on your own infrastructure, install Jentic One from its GitHub repo.