agentleFS
Sign inStart free
yingwangyingwang/cc-telegram-voice/skills/voice-reply/SKILL.md

voice-reply

Skill1 starsChanged 4 months agoMITView on GitHub

Reply to a channel message with a synthesized voice note instead of text. Use when the user explicitly asks to hear a voice reply.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write your reply as plain text.

    line 19
  2. Distinctive:

    Default to text: it is glanceable on a watch, rereadable, and searchable, and long or structured answers read better.

    line 37

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Voice Reply

Turn your text answer into a voice note with speak.py (edge-tts), then send it through the channel's reply tool as an audio attachment. The mirror image of the voice-transcribe skill.

Prerequisite (one time)

./setup.sh from the repo root installs edge-tts into .venv along with the transcription dependencies.

Steps

  1. Write your reply as plain text.

  2. Synthesize it to an mp3:

    /ABSOLUTE/PATH/TO/cc-telegram-voice/.venv/bin/python \
  /ABSOLUTE/PATH/TO/cc-telegram-voice/speak.py \
  "<your reply text>" --voice zh-CN-YunxiNeural --out reply.mp3

    Replace the path with wherever you cloned this repo. Swap --voice for any language or voice (speak.py --list-voices). Tune pace and tone with --rate and --pitch, e.g. --rate=-11% --pitch=-2Hz.

  3. Send the mp3 through the channel's reply tool as a file attachment. For the Telegram plugin that is reply with files: ["<path>/reply.mp3"].

When to use voice vs text

Default to text: it is glanceable on a watch, rereadable, and searchable, and long or structured answers read better. Reach for voice only when the user explicitly asks for it. Sending a voice note does not, on its own, mean the user wants voice back unless they say so.

Privacy

speak.py sends the text to Microsoft's endpoint to synthesize it (unlike the fully local transcribe.py). Keep anything private in text.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free