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

voice-transcribe

Skill1 starsChanged 4 months agoMITView on GitHub

Transcribe an incoming Telegram (or other) voice message to text, fully offline. Use whenever a channel message arrives with an audio attachment and you need to know what was said.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. kip-claw/skills★ 3same name
    2. jehrhardt/agents★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repositoryOne other file it gives its agents.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Download the audio: Call the Telegram plugin's download_attachment with the attachment_file_id from the channel meta.

    line 32
  2. Distinctive:

    Transcribe: Run the transcriber with the repo's virtualenv python:

    line 36
  3. Distinctive:

    Act on the transcript: Treat the printed text as if the user had typed it, and reply through the normal channel reply tool.

    line 48

≈ “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 Transcribe

Turn a voice message into text on the local machine, without sending audio to any cloud service. Backed by PyAV (decode) plus whisper.cpp (recognition).

When to use

A Telegram voice note arrives as a channel block whose meta carries an attachment_file_id and an audio mime type, for example:

<channel source="telegram" chat_id="..." attachment_file_id="AwAC..." attachment_mime="audio/ogg">
(voice message)
</channel>

You cannot read a voice note directly. Transcribe it first, then respond to the text as usual.

Prerequisite (one time)

From the repo root, run ./setup.sh. It builds whisper.cpp, downloads a model, and creates a .venv with PyAV. Nothing leaves the machine.

Steps

  1. Download the audio. Call the Telegram plugin's download_attachment with the attachment_file_id from the channel meta. It returns a local path to a .oga file.

  2. Transcribe. Run the transcriber with the repo's virtualenv python:

    /ABSOLUTE/PATH/TO/cc-telegram-voice/.venv/bin/python \
  /ABSOLUTE/PATH/TO/cc-telegram-voice/transcribe.py \
  "<downloaded .oga path>" --lang zh

    Replace /ABSOLUTE/PATH/TO/cc-telegram-voice with wherever you cloned this repo. Use --lang zh for Chinese, --lang en for English, or --lang auto to let whisper detect. The transcript is printed to stdout.

  3. Act on the transcript. Treat the printed text as if the user had typed it, and reply through the normal channel reply tool.

Notes

  • Telegram voice notes are ogg/opus; PyAV decodes them without a system ffmpeg.
  • WeChat voice messages use the SILK codec, which FFmpeg/PyAV cannot decode. Supporting WeChat voice needs an extra SILK-to-PCM step (for example the silk-v3-decoder project) ahead of transcribe.py, and depends on the WeChat channel actually exposing the raw voice file. That is out of scope for the base setup here.
  • First run on a fresh machine downloads the model (~180 MB). Later runs are local and fast.

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