BlueColumn ClawHub Integration

Integrate ClawHub with BlueColumn AI for audio ingest, memory, and semantic retrieval. Use when wiring ClawHub to push calls, music, podcasts, and voice notes through BlueColumn's …

bluecolumnconsulting-lgtm

@bluecolumnconsulting-lgtm

What This Skill Does

Integrates ClawHub with BlueColumn AI to ingest audio (calls, music, podcasts, voice notes) via the /v1/audio/ingest endpoint, with support for transcription, diarization, sentiment analysis, music analysis, and semantic retrieval. Also enables real-time audio streaming for live conversations with mid-call memory.

Replaces building custom audio pipelines and memory infrastructure by providing a pre-built integration that handles audio ingest, processing, and semantic retrieval through BlueColumn's API.

When to Use It

  • Push recorded ClawHub calls to BlueColumn for transcription and analysis
  • Ingest music files from ClawHub into BlueColumn for BPM, key, and mood detection
  • Stream live ClawHub conversations to BlueColumn for real-time mid-call memory
  • Automatically generate summaries and action items from ClawHub audio sessions
  • Enable semantic search over ClawHub audio content using BlueColumn's recall endpoint

Install

$ openclaw skills install @bluecolumnconsulting-lgtm/bluecolumn-clawhub-integration

BlueColumn ClawHub Audio Ingest Integration

BlueColumn (bluecolumn.ai) is a Memory Infrastructure API for AI agents. This skill documents how ClawHub integrates with BlueColumn for audio ingest, memory, and semantic retrieval.

Primary Endpoint

POST https://api.bluecolumn.ai/v1/audio/ingest

This endpoint handles uploaded calls, music, podcasts, voice notes, and mixed audio.

Request Format

{
  "audio_url": "https://signed-storage-url.example.com/audio-file.mp3",
  "namespace": "clawhub_audio",
  "session_id": "clawhub_call_12345",
  "user_ref": "customer_6789",
  "mode": "auto",
  "tier": "pro",
  "options": {
    "transcribe": true,
    "diarize": true,
    "detect_language": true,
    "translate_to_english": true,
    "pii_redaction": true,
    "sentiment": true,
    "extract_entities": true,
    "generate_summary": true,
    "generate_action_items": true,
    "analyze_music": true,
    "detect_bpm": true,
    "detect_key": true,
    "detect_instruments": true,
    "detect_mood": true,
    "detect_genre": true,
    "detect_sections": true,
    "generate_audio_embeddings": true,
    "generate_text_embeddings": true,
    "speaker_aware_chunking": true,
    "store_original_audio": true
  }
}

Required Fields

Every BlueColumn request must include:

  • namespace — never rely on a default
  • session_id — unique session identifier
  • user_ref — user reference
  • metadata.source = "clawhub"
  • metadata.channel — channel identifier
  • metadata.agent — agent identifier

Mode Options

ModeUse Case
"auto"Default for recorded calls
"music"For music files
"hybrid"For calls containing both speech and music

Default Audio Configuration

{
  "mode": "auto",
  "tier": "pro",
  "transcribe": true,
  "diarize": true,
  "pii_redaction": true,
  "generate_summary": true,
  "generate_action_items": true,
  "speaker_aware_chunking": true,
  "analyze_music": true,
  "store_original_audio": true
}

Webhook & Status Check

  • Receive completion through the provided webhook_url
  • If a webhook is unavailable, check: GET /v1/audio/:audio_id

Real-Time Streaming

For live conversations requiring mid-call memory:

WebSocket: wss://api.bluecolumn.ai/v1/audio/stream

Existing Integrations (Do Not Remove)

The following BlueColumn endpoints are not part of this ingest integration but must continue to work:

  • POST /v1/converse
  • POST /v1/remember
  • POST /v1/recall — semantic retrieval
  • POST /v1/note
  • GET /v1/sessions
  • GET /v1/health

Field Name Gotchas

  • /agent-remember uses text not content
  • /agent-recall uses q not query
  • /agent-note uses text not note

API Key Handling

Store the BlueColumn API key using the platform's secret store (preferred) or in TOOLS.md:

### BlueColumn
API Key: bc_live_XXXXXXXXXXXXXXXXXXXX

Keys are generated at bluecolumn.ai/dashboard. Never log or expose keys in output.

Top skills in this category

Cinematic Script Writer

@praveenspeaks

Create professional cinematic scripts for AI video generation with character consistency and cinematography knowledge. Use when the user wants to write a cinematic script, create story contexts with characters, generate image prompts for AI video tools (Midjourney, Sora, Veo), or needs cinematography guidance (camera angles, lighting, color grading). Also use for character consistency sheets, voice profiles, anachronism detection, and saving scripts to Google Drive.

97.6k

YouTube Watcher

@michaelgathara

Fetch and read transcripts from YouTube videos. Use when you need to summarize a video, answer questions about its content, or extract information from it.

34255k

Screenshot

@ivangdavila

Capture, inspect, and compare screenshots of screens, windows, regions, web pages, simulators, and CI runs with the right tool, wait strategy, viewport, and...

3818k

YouTube Transcript

@xthezealot

Fetch and summarize YouTube video transcripts. Use when asked to summarize, transcribe, or extract content from YouTube videos. Handles transcript fetching via residential IP proxy to bypass YouTube's cloud IP blocks.

2426k

Wechat Article Search

@wuchubuzai2018

搜索微信公众号文章技能。通过微信搜索获取文章列表,覆盖科技/AI、社会热点、财经、教育、职场等各类中文资讯;可按关键词检索并返回标题、概要、发布时间、来源公众号与链接。当用户需要查找微信公众号文章、整理参考资料或快速获取文章信息时使用此技能。

3317k