LaunchKit · 2026
Back to Skills

voice-log

Background voice journaling with Soniox realtime STT for OpenClaw.

2
401 downloads
by @easwee

Setup & Installation

openclaw skills install @easwee/voice-log

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install voice-log

Version History

v0.1.5Feb 22, 2026 - Version note by skill developer:

Security hardening and audio capture reliability fixes

What This Skill Does

Background daemon that captures microphone audio and transcribes it in real time using Soniox STT. Keeps a rolling 60-minute text log bucketed by minute. Responds to start/stop commands and can summarize or retrieve transcripts from any recent time window.

Runs as a background process so transcription continues without keeping a terminal session active or interrupting the current workflow.

When to use it

  • Reviewing what was discussed in a meeting after the fact
  • Capturing spoken notes during a coding or design session
  • Getting a summary of the last 10 minutes of a call
  • Logging multilingual conversations with language hints
  • Checking whether the voice journal daemon is currently running

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: summarize what we talked about for the last 15 minutes

AGENT
  1. 1Run `node scripts/voice_journal_ctl.js last 15` in the skill directory
  2. 2Receive capped transcript text from the log
  3. 3Summarize the returned text without quoting raw output
OUTPUT

A short natural-language summary of the last 15 minutes of logged speech

Requirements

Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.

SONIOX_API_KEY environment variable — get one at https://soniox.com/speech-to-text