Transcribe audio files to plain text via the Groq Whisper API.
npx skills add https://github.com/junghan0611/agent-config --skill transcribe-junghan0611
Please help me install this Agent Skill. Skill: transcribe Source: https://github.com/junghan0611/agent-config/tree/main/skills/transcribe Command: npx skills add https://github.com/junghan0611/agent-config --skill transcribe-junghan0611
Speech-to-text transcription using Groq Whisper API to convert audio content into searchable, editable text.
Run the transcribe.sh script with an audio file path to generate a transcription.
High-intent search queries and answers about installing and using this skill.
You can transcribe audio to text by running the provided script with your audio file path, which sends the audio to the Groq Whisper API and outputs the resulting plain text transcription to stdout.
Groq Whisper transcription supports m4a, mp3, wav, ogg, flac, and webm audio formats, allowing you to convert various multimedia recordings into plain text.
Yes, you need a GROQ_API_KEY and an audio file to convert speech to text, as the script relies on the Groq Whisper API for processing the audio recordings.
You can generate meeting minutes from an audio recording by providing the audio file to the script, which leverages the Groq Whisper API to deliver fast and accurate plain text transcripts.
Curl supports sending audio files for speech-to-text conversion by making the necessary HTTP requests to the Groq Whisper API using your GROQ_API_KEY and returning the text output to stdout.
The best way to get podcast notes from an m4a file is using this transcription script, which processes the m4a audio via the Groq Whisper API to produce searchable and editable plain text output.
pramudityadTranscribe audio files to plain text using the Groq Whisper API.
githubGenerate standardized meeting minutes with decisions and action items.
juliuss1907Manage Airtable records and bases via curl commands.
elizaOSTranscribe audio files locally with the Whisper CLI without API keys.
