Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
- Updated script and file locations to the new scripts/ directory for better organization. - Usage examples and documentation now reference {baseDir}/scripts/transcribe.sh. - requirements.txt, transcribe.py, and transcribe.sh moved into scripts/ directory. - Old top-level script and requirement files removed; new versions added in scripts/. - No changes to user-facing options or functionality.
What This Skill Does
Transcribes audio and video files to text using ElevenLabs Scribe. Supports batch processing of local files, realtime streaming from URLs or microphones, and speaker diarization across 90+ languages.
Handles both batch and realtime streaming in one tool, with speaker diarization and word-level timestamps that most transcription wrappers omit.
When to use it
- Transcribing recorded meetings with speaker labels
- Capturing live voice input during an agent session
- Converting podcast or radio streams to text in realtime
- Extracting subtitles from video files with word timestamps
- Batch transcribing interview recordings for analysis
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: transcribe this meeting recording and identify who said what
- 1Receives meeting.mp3 as input
- 2Runs transcribe.sh meeting.mp3 --diarize --json
- 3ElevenLabs Scribe API processes the audio and returns speaker-labeled segments
- 4Parses JSON output to extract text grouped by speaker_id
- 5Returns formatted transcript with speaker attribution
Full transcript with each speaker's lines labeled as speaker_0, speaker_1, etc., including word-level timestamps
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.