groq-voice

Transcribe .ogg voice messages into text using the Groq Whisper API.

3|1|Updated May 21, 2026
One-click install
npx skills add https://github.com/qwwiwi/agentos-skills-public --skill groq-voice
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: groq-voice
Source: https://github.com/qwwiwi/agentos-skills-public/tree/main/skills/groq-voice
Command: npx skills add https://github.com/qwwiwi/agentos-skills-public --skill groq-voice

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

It solves the problem of converting user voice messages into readable text so you can respond accurately without manually playing audio.

Core Features & Use Cases

  • Audio-to-Text Transcription: Converts attached .ogg audio from media tags into a transcript for understanding.
  • Groq Whisper API Integration: Uses Groq’s Whisper transcription model for fast and accurate results, including Russian.
  • Workflow Trigger: Automatically runs transcription whenever a message contains media:audio and then uses the transcript for the reply.

Quick Start

Send a voice message that includes the media:audio tag so the skill transcribes the attached .ogg file and then you can respond naturally to the spoken content.

Frequently Asked Questions about groq-voice

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I transcribe .ogg voice messages into readable text?

Transcribe .ogg voice messages by extracting the audio file path from the media attachment line and running it through the Groq Whisper API. The skill converts spoken audio into a text transcript for downstream conversational responses.

Does audio to text transcription work with Russian voice messages?

Yes, audio to text transcription supports Russian voice messages. The skill uses Groq's Whisper transcription model to provide fast and accurate results for Russian and other spoken languages in .ogg files.

How do I automatically trigger transcription when a chat includes audio attachments?

Automatic transcription triggers whenever a message contains a media audio attachment. The skill detects the media tag, extracts the .ogg file path, and processes the voice message to generate text for replying naturally.

What do I need to run Groq Whisper transcription on .ogg files?

Running Groq Whisper transcription requires an authorization Bearer key for the API. You provide the key, and the skill extracts the .ogg media attachment path to process the audio file and output text.

Can I use this transcription for research note-taking from spoken input?

Yes, you can use this transcription for research note-taking. The skill converts spoken input from .ogg media attachments into readable text, fitting any chat workflow where users provide voice messages for documentation.

Why is my .ogg voice message not transcribing into text?

Your .ogg voice message may not transcribe if the media attachment tag is missing or the Groq authorization Bearer key is invalid. The skill requires extracting the exact .ogg file path from the media line to run Whisper transcription.