Skip to content
Get packs

Voice Call Post-Processing

Turns a finished voice call into a saved transcript, summary, and audio link in your brain.

Source Download skill
Repository
garrytan/gbrain
Stars
31,447
Licence
MIT
Files
1 file

What it does

When a voice call with an AI persona ends, this skill tells the agent how to process it: transcribe the audio, write a summary and verbatim transcript into a meeting page in the knowledge base, link any people or companies mentioned, and post a short summary to a messaging app. It is a blueprint more than a finished tool, because the automatic call-end trigger is not shipped and the operator has to wire it up in their own host repository.

Great for

  • Developers building a voice assistant on top of gbrain who want call records saved automatically
  • Operators who already run the gbrain voice-agent service and want a consistent post-call record format

Skip it if

  • People who just want a call summary from a phone app: this needs a self-hosted voice-agent setup and its own transcription and messaging wiring
  • Calls that must stay private: the pipeline stores full verbatim transcripts and audio files and posts summaries to external messaging services, and the file does not describe consent or retention controls

Try asking

  • “Summarize the call I just finished with Venus and save it to my brain”
  • “Write the post-call summary and transcript for today's voice session”
  • “Log this voice call under meetings and link any people mentioned”
Step-by-step guide: how to use Voice Call Post-ProcessingInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the MIT licence and an attribution note.

    voice-post-call.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip voice-post-call.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip voice-post-call.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Expect calls to be processed only if the persona logs them mid-call unless you build the call-end handler described in the file
  • Check the relative links to gbrain conventions files, since they only resolve if your repo mirrors gbrain's skills layout

What's inside

  • SKILL.md

Redistributed unmodified from garrytan/gbrain under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.