transcribe
Speech-to-text transcription using Groq Whisper API. Supports m4a, mp3, wav, ogg, flac, webm.
When & Why to Use This Skill
This Claude skill leverages the high-performance Groq Whisper API to provide lightning-fast and accurate speech-to-text transcription. It enables users to convert various audio formats—including m4a, mp3, wav, and more—into clean, punctuated text. By automating the transcription process, it significantly reduces the manual effort required to digitize voice data, making it an essential tool for workflows involving audio analysis and documentation.
Use Cases
- Meeting Minutes: Convert recorded business meetings or voice memos into text to quickly generate summaries and action items.
- Content Creation: Transcribe podcasts, video scripts, or interviews to repurpose audio content into blog posts, articles, or social media captions.
- Academic & Research: Streamline the transcription of qualitative interviews or lectures for easier data coding and analysis.
- Accessibility: Generate text transcripts for audio files to ensure content is accessible to individuals with hearing impairments and compliant with web standards.
| name | transcribe |
|---|---|
| description | Speech-to-text transcription using Groq Whisper API. Supports m4a, mp3, wav, ogg, flac, webm. |
Transcribe
Speech-to-text using Groq Whisper API.
Setup
The script needs GROQ_API_KEY environment variable. Check if already set:
echo $GROQ_API_KEY
If not set, guide the user through setup:
- Ask if they have a Groq API key
- If not, have them sign up at https://console.groq.com/ and create an API key
- Have them add to their shell profile (~/.zshrc or ~/.bashrc):
export GROQ_API_KEY="<their-api-key>" - Then run
source ~/.zshrc(or restart terminal)
Usage
{baseDir}/transcribe.sh <audio-file>
Supported Formats
- m4a, mp3, wav, ogg, flac, webm
- Max file size: 25MB
Output
Returns plain text transcription with punctuation and proper capitalization to stdout.