OpenSkillIndex← back to search
claude-code

Skills transcription

Transcribe audio and video files using the Signal Loom AI API. Supports MP3, WAV, M4A, MP4, MOV, and more. Runs locally on Apple Silicon for speed and privacy.

install
source · Clone the upstream repo
git clone https://github.com/openclaw/skills
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/openclaw/skills "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/avale-slai/signalloom-transcription" ~/.claude/skills/clawdbot-skills-transcription && rm -rf "$T"
manifest: skills/avale-slai/signalloom-transcription/SKILL.md
source content

Transcription — Signal Loom AI

What It Does

Transcribes media files to structured JSON, SRT, VTT, and plain text — all in a single pass. Local processing on Apple Silicon means audio never leaves your machine.

When to Use

  • Transcribing meeting recordings, podcasts, or videos
  • Converting spoken content to searchable text
  • Processing audio for AI agent pipelines
  • Subtitles and captions for video content

Syntax

/transcribe ./meeting-recording.mp3 --format json
/transcribe ./podcast.mp4 --language en

Free Tier

100 minutes/month free with any Signalloom API key.

Get your free key: https://signalloomai.com/signup

Output Formats

  • JSON: Timestamped words, confidence scores, speaker diarization
  • SRT/VTT: Subtitles ready for video players
  • Plain text: Clean transcript