agentleFS
qwwiwiqwwiwi/agentos-skills-public/skills/groq-voice/SKILL.md

groq-voice

Skill4 starsChanged 4 months agoMITView on GitHub

Transcribe voice messages (.ogg) via Groq Whisper API. When you see <media:audio> in a message, extract the file path and transcribe it using the included script.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 6 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    When you receive a message containing <media:audio> tag, it means the user sent a voice message.

    line 8
  2. Very specific:

    When you see <media:audio>, you MUST:

    line 12
  3. Distinctive:

    Run the transcription script:

    line 15
  4. Distinctive:

    Use the transcript text to understand what the user said

    line 19
  5. Distinctive:

    Do NOT mention the transcription process unless asked

    line 21
  6. Distinctive:

    Always transcribe first, then respond to the content

    line 24
  7. Distinctive:

    If transcription fails, tell the user you couldn't process their voice message

    line 26
  8. Distinctive:

    Do NOT say "I can't listen to audio" — you CAN via this script

    line 27

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Groq Voice Transcription

When you receive a message containing <media:audio> tag, it means the user sent a voice message. The audio file path is in the [media attached: PATH] line.

MANDATORY: Transcribe BEFORE responding

When you see <media:audio>, you MUST:

  1. Extract the .ogg file path from the [media attached: /path/to/file.ogg ...] line
  2. Run the transcription script:
exec 'bash ~/.claude/skills/groq-voice/transcribe.sh "/path/to/file.ogg"'
  1. Use the transcript text to understand what the user said
  2. Respond to the user's spoken message naturally
  3. Do NOT mention the transcription process unless asked

Important

  • Always transcribe first, then respond to the content
  • The script uses Groq Whisper API (fast, accurate, supports Russian)
  • If transcription fails, tell the user you couldn't process their voice message
  • Do NOT say "I can't listen to audio" — you CAN via this script

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.