Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
tag 1.2.0 Tagger: Ilya Kaminsky <ilyakam@gmail.com> ## [1.2.0] - 2026-02-01 ### Added - Add `publish.sh` script for publishing the skill to ClawHub ### Fixed - Ensure the script is executable by publishing it with OpenClaw
What This Skill Does
Automatic speech-to-text transcription via the Speech is Cheap API. Supports 100 languages with auto-detection, speaker diarization, word-level timestamps, and multiple output formats including SRT, VTT, and JSON. Handles both remote URLs and local file uploads.
At $0.06-$0.12 per hour, it undercuts Deepgram and OpenAI Whisper API pricing by 2-15x while transcribing 100 minutes of audio in roughly one minute.
When to use it
- Transcribing recorded meetings or interviews
- Generating subtitles for video content
- Processing large batches of podcast episodes
- Converting voice memos to searchable text
- Building automated pipelines that ingest audio and output structured transcripts
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: transcribe this podcast episode and output an SRT file
- 1Receive the audio URL from the user
- 2Run asr.sh transcribe --url with --format srt and --words flags
- 3Poll job status using asr.sh status if transcription is async
- 4Receive JSON response with SRT-formatted transcript
- 5Return the subtitle file to the user
An SRT file with timestamped captions ready for video editing or publishing
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.