asr
by ilyakam
Browser & AutomationBrief
Fast, accurate, and incredibly inexpensive automatic speech-to-text.
Description
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
User asks: transcribe this podcast episode and output an SRT file
- 1
Receive the audio URL from the user
- 2
Run asr.sh transcribe --url with --format srt and --words flags
- 3
Poll job status using asr.sh status if transcription is async
- 4
Receive JSON response with SRT-formatted transcript
- 5
Return the subtitle file to the user
An SRT file with timestamped captions ready for video editing or publishing
Requirements
- SIC_API_KEY environment variable
- speechischeap.com account
Installation
clawhub install ilyakam/asrRun the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.