# AI use cases for Frametell (sitor-ai/frametell)

Repo: [sitor-ai/frametell](https://github.com/sitor-ai/frametell) | Use cases: 3 | Page: https://dedupedai.com/use-cases/sitor-ai-frametell/

Frametell is an open source TypeScript tool that turns an idea or source material into a narrated explainer video, with an AI director agent drafting a storyboard you approve before rendering.

This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL.

- Make an explainer video from one sentence: https://dedupedai.com/use-cases/sitor-ai-frametell/explainer-video-from-one-sentence/
- Turn your notes or PDF into an explainer video: https://dedupedai.com/use-cases/sitor-ai-frametell/turn-notes-or-pdf-into-explainer-video/
- Have an agent render an explainer from a command: https://dedupedai.com/use-cases/sitor-ai-frametell/script-and-render-explainer-from-agent-workflow/

## How to make an explainer video from one sentence with Frametell

Repo: [sitor-ai/frametell](https://github.com/sitor-ai/frametell) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Type a topic, approve the storyboard, and get a 1080p narrated MP4 with subtitles.

**Who it is for:** A knowledge creator who needs a short explainer on a topic today and does not want to learn video editing.

**The problem:** Producing a narrated explainer takes scripting, voiceover, slide design and editing, which slows down a solo creator.

**The outcome:** A finished 1080p MP4 with subtitles and publishing notes, built from a single sentence after you sign off on the storyboard.

### Steps

1. Download the macOS app from the latest release, or run `git clone https://github.com/sitor-ai/frametell.git && cd frametell`.
2. If running from source, run `pnpm install && pnpm build`.
3. Set a provider key, for example `export ANTHROPIC_API_KEY=...`, and optionally `export ELEVENLABS_API_KEY=...`.
4. Run `node apps/cli/dist/cli.js serve` and open the studio in your browser.
5. Enter your sentence, review the storyboard pages, edit anything that is wrong, then approve it so the narration, voice, pages and render can run.

### Prompt to paste into your agent

```text
Use the Frametell repo at sitor-ai/frametell. Build it with pnpm install and pnpm build, then start the studio with node apps/cli/dist/cli.js serve and create a video about <topic> in English. Expected output: a 1080p MP4 with subtitles; verify that the storyboard was shown for approval before any pages were drawn.
```

### Caveat

The macOS app covers only Apple Silicon Macs for now, so Windows and Intel Mac users must run from source.

Risk, credentials: Model provider and ElevenLabs API keys are entered as environment variables or in Settings, so keep them out of shared shells, logs and screenshots.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/sitor-ai-frametell/explainer-video-from-one-sentence/

## How to turn your notes or PDF into an explainer video with Frametell

Repo: [sitor-ai/frametell](https://github.com/sitor-ai/frametell) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Point Frametell at a document or slides and render a narrated video in a chosen style.

**Who it is for:** A researcher or course author with lecture notes, a PDF or a slide deck who wants a video version without rebuilding the material by hand.

**The problem:** Existing notes and slides are not in a format that can be narrated and animated, so repurposing them takes manual work.

**The outcome:** A narrated MP4 built from your own material in a style you pick, with a 60 second target length in the example.

### Steps

1. Install Frametell from source with `git clone https://github.com/sitor-ai/frametell.git && cd frametell` and `pnpm install && pnpm build`.
2. Set your model provider key, for example `export ANTHROPIC_API_KEY=...`.
3. Run `node apps/cli/dist/cli.js run notes.pdf --style warm-story --duration 60 --lang en` with your own file in place of notes.pdf.
4. Check the storyboard the director produces, since you can approve or edit pages before the film is rendered.
5. Open the rendered 1080p MP4 and review the subtitles before publishing.

### Prompt to paste into your agent

```text
Use the Frametell repo at sitor-ai/frametell after running pnpm install and pnpm build. Run node apps/cli/dist/cli.js run <file> --style warm-story --duration 60 --lang en to turn <file> into an explainer video. Expected output: a 1080p MP4 with subtitles; verify that the narration covers the main points of the source file.
```

### Caveat

The README gives the run command with notes.pdf, style, duration and language flags only, so check the command help before depending on other options.

Risk, credentials: Your source files and API keys stay on your computer, but any keys you export into the shell can leak through shared terminal history.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/sitor-ai-frametell/turn-notes-or-pdf-into-explainer-video/

## How to have an agent render an explainer from a command with Frametell

Repo: [sitor-ai/frametell](https://github.com/sitor-ai/frametell) | Difficulty: Advanced | Time: 45 minutes | Basis: From the README

Let a coding agent run the Frametell CLI to produce a narrated MP4 from a source file.

**Who it is for:** A developer or content operator who wants an agent to produce explainer videos as part of a repeatable workflow on their own machine.

**The problem:** Manually opening the studio for every video is slow when the same kind of explainer has to be made again and again.

**The outcome:** An agent runs the Frametell CLI and returns a rendered 1080p MP4 file path for review.

### Steps

1. Clone the repo with `git clone https://github.com/sitor-ai/frametell.git && cd frametell`.
2. Run `pnpm install && pnpm build` and confirm Chrome, Edge or Chromium is installed.
3. Export the model provider key in the shell, for example `export ANTHROPIC_API_KEY=...`.
4. Run `node apps/cli/dist/cli.js run notes.pdf --style warm-story --duration 60 --lang en` with the agent's target file.
5. Review the storyboard and the finished film, since the README says the director drafts a storyboard for sign-off before pages are drawn.

### Prompt to paste into your agent

```text
Use the Frametell repo at sitor-ai/frametell, after pnpm install and pnpm build. Run node apps/cli/dist/cli.js run <file> --style <style> --duration <seconds> --lang <lang> and report the path to the rendered 1080p MP4. Verify that subtitles are present and that the film matches the approved storyboard.
```

### Caveat

The README describes approval of the storyboard in the studio flow, so a fully unattended CLI run may skip the review step the README emphasises.

Risk, credentials: An agent running the CLI needs provider keys in its environment, so scope those keys to this task and avoid letting the agent print them.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/sitor-ai-frametell/script-and-render-explainer-from-agent-workflow/