read-aloud-edge-tts

read-aloud-edge-tts is a skill for Claude Code, Codex from usefulmove/enso. It costs 43 tokens per session (653 once invoked), scanned A, original, MIT.

A tool workflow for turning text or Markdown files into spoken audio with the edge-tts command-line tool.

In plain words
What is it for?
Use it to check for edge-tts, clean text or Markdown, join lines naturally, and play the generated speech with an audio player.
Why use it?
It makes long documents easier to consume without reading them on screen and removes Markdown formatting that would sound awkward aloud.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions OpenCode.

Good fit Use it to check for edge-tts, clean text or Markdown, join lines naturally, and play the generated speech with an audio player.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/usefulmove/enso/read-aloud-edge-tts
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add usefulmove/enso --skill read-aloud-edge-tts
Clone the repo
git clone --depth 1 https://github.com/usefulmove/enso

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for read-aloud-edge-tts

README.md
[![agentmods](https://agentmods.dev/badge/skills/usefulmove/enso/read-aloud-edge-tts/github.svg)](https://agentmods.dev/skills/usefulmove/enso/read-aloud-edge-tts)
Your own site
<a href="https://agentmods.dev/skills/usefulmove/enso/read-aloud-edge-tts"><img src="https://agentmods.dev/badge/skills/usefulmove/enso/read-aloud-edge-tts/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for read-aloud-edge-tts

Your own site · 80×15
<a href="https://agentmods.dev/skills/usefulmove/enso/read-aloud-edge-tts"><img src="https://agentmods.dev/badge/skills/usefulmove/enso/read-aloud-edge-tts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 653 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.00653
Opus 5 $0.00022 $0.00327
Sonnet 5 $0.00009 $0.00131
Haiku 4.5 $0.00004 $0.00065

Measured 10d ago against content hash 32a12ef5acd1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

read-aloud-edge-tts scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/read-aloud-edge-tts/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When to Use

  • The user asks you to "read this file to me" or "read this aloud".
  • The user is having trouble reading a long markdown document and wants an audio version.
  • The user wants to listen to the contents of a text file while doing something else.

Workflow

1. Check for edge-tts

Before attempting to read a file, ensure edge-tts is installed on the system. Run:

which edge-tts

If it is not found, install it using pipx (recommended for isolated CLI tools):

pipx install edge-tts

2. Prepare the Text

If the file is a Markdown file, you should strip the formatting characters (like #, *, _) so the TTS engine doesn't read them out loud as "hash hash hash".

Always collapse newlines to spaces before reading. TTS engines treat \n as a pause marker, which makes poetry and formatted text sound choppy. Pipe through tr '\n' ' ' | sed 's/ */ /g' to produce natural flowing speech.

3. Read Aloud

Use a bash pipeline to read the file, strip formatting (if necessary), and pipe it to edge-tts, which then pipes the audio to ffplay (or another audio player like mpv or aplay).

For Markdown files:

cat <file_path> | sed -e 's/[#*_]//g' | tr '\n' ' ' | sed 's/  */ /g' | edge-tts --voice en-US-AriaNeural --file - | ffplay -nodisp -autoexit -loglevel quiet -i -

For plain text files:

cat <file_path> | tr '\n' ' ' | sed 's/  */ /g' | edge-tts --voice en-US-AriaNeural --file - | ffplay -nodisp -autoexit -loglevel quiet -i -

Note: en-US-AriaNeural is a high-quality default voice. Other good options include en-US-ChristopherNeural or en-GB-SoniaNeural.

4. Handle Audio Issues

If the command succeeds but the user reports hearing no sound, advise them that it might be a system audio issue (e.g., PulseAudio or PipeWire configuration) and suggest they check their volume and output device settings.


Checklist

  • edge-tts is installed and available in the PATH.
  • Markdown formatting is stripped before reading (if applicable).
  • Newlines are collapsed to spaces for natural speech flow.
  • The file is successfully read aloud using edge-tts.

Read the full file on GitHub · 60 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 60 lines · 43 tokens per session scan A 32a12ef5acd1

Subscribe to this mod's changes

read-aloud-edge-tts is a skill published in the GitHub repository usefulmove/enso (2 stars, last pushed 3mo ago), licensed MIT. It adds 43 tokens to every session and 653 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

obsidian-cli

Obsidian vault integration via official CLI. Use when: capturing dev artifacts to Obsidian vault, searching vault for context, appending to daily note, managing tasks in vault. Not for: general note-taking without Obsidian (use regular files), browsing Obsidian docs (use agent-browser). Output: vault search results…

sd0xdev/sd0x-harness · 78 tokens

lastMonth

Resolve "lastMonth" to a concrete ISO date range relative to your run time — the previous full calendar month. Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a task over last month (monthly reports…

chaitanyagiri/munder-difflin · 73 tokens

lastYear

Resolve "lastYear" to a concrete ISO date range relative to your run time — the previous full calendar year. Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a task over last year (annual reports…

chaitanyagiri/munder-difflin · 73 tokens

google-workspace

Manage Gmail, Google Calendar, Drive, Sheets, Docs, Contacts, and Tasks via the gogcli CLI. TRIGGER: "gmail", "google calendar", "google drive", "google sheets". NOT FOR: outlook-assistant, xlsx, docx use cases.

xg-gh-25/SwarmAI · 61 tokens

todo

Create and update the Hyper-Waterfall daily task board (mydocs/orders/yyyymmdd.md). Apply milestone table format, status update rules, and backlog section rules. When task-start, task-stage-report, task-final-report, or pr-merge-cleanup updates the daily task board, it follows this SKILL's format.

postmelee/hyper-waterfall · 71 tokens

expense-report-generation

How to turn raw card and bank statement downloads into a defensible, client-ready expense report. Use whenever the user asks to build an expense report, reconcile AmEx or bank statements, work out "what is this charge for", aggregate reimbursables for a client or trip, split a claim by month, or render an expense PDF…

lossless-group/lossless-agent-skills · 181 tokens