text-to-video · pexoai — Claude Code skill: what it does, how to install
text-to-video turns a written prompt or script into a finished video with multiple shots, music, and subtitles. Use it when the video should start from text.
MIT 127 installs ★ 835 updated 2026-08-20
npx skills add pexoai/pexo-skills --skill text-to-video -a claude-codeWhat text-to-video does
This skill sends a prompt or script to Pexo’s hosted agent. Pexo writes the script, selects a model for each shot from 10+ engines, renders the shots, and adds music, subtitles, and transitions.
The bundled scripts create a project, upload supplied files, send the request, poll its state, and fetch the final asset. Pexo cannot fetch files from URLs on its own, so download them before uploading and attach the required asset tag. The setup needs PEXO_API_KEY and PEXO_BASE_URL in ~/.pexo/config, plus curl, jq, and file. It is for text-to-video work, not for editing an existing video or animating an image.
What it helps with
- create a video from a written brief
- turn a script into a multi-shot video
- add music and subtitles to a generated video
- upload source files to a Pexo project
- retrieve the rendered video asset
Example prompts for the agent
- Create a video from this brief: a short launch piece for our coffee subscription.
- Turn the script in
script.txtinto a finished video with music and subtitles. - Make a video from this description and use the uploaded
logo.pngfile.
How to install text-to-video
1Skills CLI (Vercel)
npx skills add pexoai/pexo-skills --skill text-to-video -a claude-code2Manually: put the files in place
~/.claude/skills/text-to-video/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/text-to-video/
1Skills CLI (Vercel)
npx skills add pexoai/pexo-skills --skill text-to-video -a codex2Manually: put the files in place
.agents/skills/text-to-video/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add pexoai/pexo-skills --skill text-to-video -a cursor2Manually: put the files in place
.cursor/skills/text-to-video/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install pexoai/pexo-skills skills/text-to-video2Manually: put the files in place
.github/skills/text-to-video/SKILL.md1Skills CLI (Vercel)
npx skills add pexoai/pexo-skills --skill text-to-video -a gemini-cli2Platform CLI
gemini skills install https://github.com/pexoai/pexo-skills --path skills/text-to-videoManually: put the files in place
.devin/skills/text-to-video/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add pexoai/pexo-skills --skill text-to-video -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about text-to-video
How do I install text-to-video in Claude Code?
Run npx skills add pexoai/pexo-skills --skill text-to-video -a claude-code, then check ~/.claude/skills/text-to-video/SKILL.md.
What does text-to-video do?
It sends a text request or script to Pexo, which chooses models for individual shots, renders the video, and adds music, subtitles, and transitions.
What does text-to-video need before it can run?
Set PEXO_API_KEY and PEXO_BASE_URL in ~/.pexo/config. The runtime also needs curl, jq, and file, and rendering uses Pexo credits.
Source text
SKILL.md · MIT
---
name: text-to-video
description: >
Turn a text prompt or script into a finished, multi-shot video with Pexo. Auto-selects the
best model across 10+ engines (Seedance, Kling, Veo, Sora), writes the prompts, generates
every shot, and returns a publish-ready video with music and subtitles. Use when the user
wants a video FROM TEXT: "make a video about X", "turn this script into a video", "text to
video", "generate a video from this description". NOT for editing an existing video or
turning an image into video (use the image-to-video skill).
homepage: https://pexo.ai
repository: https://github.com/pexoai/pexo-skills
version: "0.1.0"
requires:
env: [PEXO_API_KEY, PEXO_BASE_URL]
runtime: [curl, jq, file]
metadata:
author: pexoai
---
# Text to Video — Pexo
**Pexo:** https://pexo.ai — get an API key, watch your project render, and buy credits there.
Turn a written prompt or script into a finished, publish-ready video. You do not generate
anything yourself: you hand the request to the hosted Pexo agent (same backend as `pexo-agent`,
scoped to text-to-video) and deliver the result. Pexo writes the script, picks the best model
per shot, generates every shot, and adds music, subtitles, and transitions.
## Your role: relay, don't create
Create a project, send the user's request **verbatim**, poll, deliver. Pexo's backend handles
all creative work — scriptwriting, model choice, prompts, music. Adding your own direction
(duration, style, models the user didn't ask for) overrides its judgment and produces worse
videos.
## Config
`~/.pexo/config`:
```
PEXO_BASE_URL="https://pexo.ai"
PEXO_API_KEY="sk-<your-api-key>"
```
**No account / first run →** read `references/SETUP-CHECKLIST.md` and walk the user through it — it carries the signup flow with the **invite code that grants new users bonus credits**, plus how to create the config above. **Config error →** run `scripts/pexo-doctor.sh` and follow its output.
## Workflow
Scripts live in this skill's `scripts/`. Reply to the user in their language.
1. **Create a project:** `pexo-project-create.sh "<short brief>"` → save the `project_id`.
2. **Upload any files** the user gave: `pexo-upload.sh <project_id> <path>` → save `asset_id`,
reference it inline as `<original-image>asset_id</original-image>` (or `<original-video>` /
`<original-audio>`). Tags are required — a bare `asset_id` is ignored. Pexo can't crawl URLs —
download, then upload.
3. **Send the request:** `pexo-chat.sh <project_id> "<user's exact words> <asset tags>"`.
Copy the user's words exactly; only add asset tags.
4. **Tell the user** (their language): submitted ✓ · ~15–20 min · `https://pexo.ai/project/<project_id>`.
5. **Poll:** every ≥60s run `pexo-project-get.sh <project_id>` and act on `nextAction`:
- **WAIT** → keep polling; every ~5 polls send a one-line update with the project link.
- **RESPOND** → handle each event in `recentMessages`: relay Pexo's text (wait for the
user's answer if it asked, then `pexo-chat.sh` their reply); for `preview_video`, run
`pexo-asset-get.sh <project_id> <assetId>` per option, show the URLs (A/B/C), let the user
pick, then `pexo-chat.sh <project_id> "<choice>" --choice <assetId>`; for a `document`
event, mention it to the user.
- **DELIVER** → `pexo-asset-get.sh <project_id> <final assetId>`, then send the user the
**full** asset URL as plain text — all `?…` query params, never truncated or wrapped in
markdown — plus the project link.
- **FAILED** → explain `nextActionHint` in plain terms and offer to retry.
- **RECONNECT** → `pexo-chat.sh <project_id> "continue"`, tell the user the connection
dropped and you're resuming, then keep polling.
- Never call `pexo-chat.sh` during WAIT — it triggers duplicate production.
- **Taking too long** → if it's been >30 min and still WAIT, tell the user (with the project
link + `https://pexo.ai/connect/openclaw`) it's running long; ask whether to keep waiting or
stop. Don't poll forever.
## Revisions
After delivery, the user's tweaks ("make it shorter", "new music", "different shot") reuse the
**same** project: `pexo-chat.sh <project_id> "<their feedback>"`, then poll again (step 5). Never
create a new project for a revision — it throws away Pexo's server-side context.
## Credits
If a script fails with "Credits balance" / "Insufficient credits": if the error carries a
purchase link, pass it to the user; otherwise tell them to add credits at `https://pexo.ai/home`
→ Credits → Buy Credits. Retry after they confirm.
## Example
User: "Make a 30-second video about our new coffee subscription."
```bash
pid=$(pexo-project-create.sh "coffee subscription promo")
pexo-chat.sh "$pid" "Make a 30-second video about our new coffee subscription."
# Tell the user: submitted, ~15–20 min, https://pexo.ai/project/$pid
# Poll pexo-project-get.sh "$pid" until nextAction is DELIVER, then deliver the asset URL.
```
## Scripts
| Script | Usage | Returns |
|---|---|---|
| `pexo-project-create.sh` | `"<brief>"` | `project_id` |
| `pexo-upload.sh` | `<project_id> <file>` | `asset_id` |
| `pexo-chat.sh` | `<project_id> "<message>" [--choice <id>]` | ack (async) |
| `pexo-project-get.sh` | `<project_id>` | JSON: `nextAction`, `recentMessages` |
| `pexo-asset-get.sh` | `<project_id> <asset_id>` | JSON with `url` |
| `pexo-doctor.sh` | — | setup diagnostic |
Error codes and edge cases → `references/TROUBLESHOOTING.md`.
© pexoai · MIT · pexoai/pexo-skills
Similar skills
All skills for AI and ML →text-to-video by other authors comes first.