Installable skillMIT

Force-align narration and transcript text into subtitle or SMIL timing maps

Use aeneas when an agent already has audio and text, but still needs timing. The workflow aligns spoken narration against fragments of plain text or XML and emits sync maps that can be turned into subtitles, EPUB 3 media overlays, JSON timing data, or other downstream caption assets.

BY agentskillexchangeUPDATED Oct 27, 2026
INTENDED FOR◈OpenClawInstall in a listed agent.

instructions.md

---
name: force-align-narration-and-transcript-text-into-subt-566177052f7b
slug: "force-align-narration-and-transcript-text-into-subtitle-or-smil-timing-maps"
description: "Use aeneas when an agent already has audio and text, but still needs timing. The workflow aligns spoken narration against fragments of plain text or XML and emits sync maps that can be turned into subtitles, EPUB 3 media overlays, JSON timing data, or other downstream caption assets."
github_stars: 2820
verification: "security_reviewed"
source: "https://github.com/readbeyond/aeneas"
author: "Alberto Pettarin"
publisher_type: "Open Source Project"
category: "Media & Transcription"
framework: "Multi-Framework"
tool_ecosystem:
  github_repo: "readbeyond/aeneas"
  github_stars: 2820
---

# Force-align narration and transcript text into subtitle or SMIL timing maps

Use aeneas when an agent already has audio and text, but still needs timing. The workflow aligns spoken narration against fragments of plain text or XML and emits sync maps that can be turned into subtitles, EPUB 3 media overlays, JSON timing data, or other downstream caption assets.

## Prerequisites

Python, pip, FFmpeg, and eSpeak

## Installation

Use the upstream install or setup path that matches your environment:
- pip install numpy
- pip install aeneas

Requirements and caveats from upstream:
- **aeneas** is a Python/C library and a set of tools to automagically synchronize audio and text (aka forced alignment).
- Quick Links: [Home](http://www.readbeyond.it/aeneas/) - [GitHub](https://github.com/readbeyond/aeneas/) - [PyPI](https://pypi.python.org/pypi/aeneas/) - [Docs](http://www.readbeyond.it/aeneas/docs/) - [Tutorial](http:...
- [Python](https://python.org/) 2.7 (Linux, OS X, Windows) or 3.5 or later (Linux, OS X)

Basic usage or getting-started notes:
- For example, given
- All-in-one installers are available for Mac OS X and Windows,
- and a Bash script for deb-based Linux distributions (Debian, Ubuntu)

- Source: https://github.com/readbeyond/aeneas
- Extracted from upstream docs: https://raw.githubusercontent.com/readbeyond/aeneas/HEAD/README.md

## Documentation

- https://readbeyond.it/aeneas/

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/force-align-narration-and-transcript-text-into-subtitle-or-smil-timing-maps/)
COMPATIBILITY & REFERENCES

Platform guidance

Imported from the listed AgentSkill.sh category. Complete supplied package files and notices are retained. Required external tools and credentials are not installed. No bundled code was executed during import. Individual agent task behavior has not been tested.