skills.rest
bish-x
bish-xCOMMUNITY
Explore all skills by this author →
GitHub

voice-post-call

Transcribe voice calls into Markdown transcripts and structured summaries.

2|1|Updated Jun 16, 2026
Search Tags:#data management#transcription#summary generation#voice call#call logging
One-click install
npx skills add https://github.com/bish-x/bx-gbrain --skill voice-post-call-bish-x
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: voice-post-call
Source: https://github.com/bish-x/bx-gbrain/tree/main/recipes/agent-voice/skills/voice-post-call
Command: npx skills add https://github.com/bish-x/bx-gbrain --skill voice-post-call-bish-x

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires whisper, llm, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill automates the post-processing of voice calls, turning transcripts into structured data and summaries, and managing the associated files and references.

Core Features & Use Cases

  • Transcript Creation: Transcribes audio from voice calls into Markdown-formatted transcripts.
  • Summary Generation: Produces a summary of the call, capturing key points and decisions.
  • Data Management: Creates and updates brain pages with the call summary, transcript, and audio reference.
  • Use Case: Ideal for managing call logs in a team environment, where the summary and key points can be quickly accessed.

Quick Start

Use the voice-post-call skill to summarize and archive the transcript from the last voice call.

Frequently Asked Questions about voice-post-call

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate voice call transcription and summary generation for call logs?▼

Automate voice call transcription and summary generation by processing audio through Whisper to create Markdown transcripts, then using an LLM to extract key points and decisions into structured data. This workflow manages associated files and references automatically.

Do I need Whisper and an LLM to generate post-call summaries from voice sessions?▼

Yes, Whisper is required for audio transcription to convert voice sessions into text, and an LLM is required for summary generation to process the transcript into structured Markdown brain pages capturing key points and decisions.

What is the best way to manage voice call transcripts and audio references in a team environment?▼

Manage voice call transcripts and audio references by creating and updating structured Markdown brain pages. This approach archives the call summary, transcript, and audio reference together, allowing team members to quickly access key points from voice sessions.

Can I convert voice call audio directly into Markdown-formatted transcripts?▼

Yes, voice call audio is transcribed directly into Markdown-formatted transcripts using Whisper. The system operates within voice call handling systems to provide comprehensive post-call analysis and structured data management.

What are the limitations of using automated transcription for post-call analysis?▼

Automated transcription for post-call analysis requires both Whisper for audio processing and an LLM for summarization. It operates within voice call handling systems and focuses on post-processing, meaning it depends on existing audio input quality and system integration.

Related Skills

Explore More Product & Management Skills→
steipetesteipete
385.7k

openai-whisper

Transcribe local audio files to text or subtitles using the Whisper CLI.

Community
Intermediate
weipingweiping
1

voice-post-call

Convert completed voice sessions into searchable meeting pages with transcripts and summaries.

Community
Advanced
yunusgungoryunusgungor

voice-note-ingest

Route voice notes into structured brain pages with verbatim transcripts.

Community
Intermediate
inbrainfuninbrainfun
174

voice-post-call

Ingest voice-call transcripts into brain pages with summaries and audio links.

Community
Advanced