About

Imported from codemo1991/nanobot-webui (nanobot/skills/voice-transcribe/SKILL.md). Install upstream with npx skills add codemo1991/nanobot-webui --skill voice-transcribe. Copyright stays with the author.

Voice Transcription Skill

Name: voice-transcribe
Author: codemo1991

Receive voice/audio files and transcribe them to text using Groq Whisper API.

When to Use

Use voice-transcribe tool for:

Voice message transcription - Convert voice messages to text
Audio file transcription - Transcribe audio files (mp3, wav, m4a, etc.)
Meeting recording transcription - Convert meeting recordings to text

Usage

The voice_transcribe tool handles the entire workflow:

Receives the audio file
Calls Groq Whisper API for transcription
Returns the transcribed text

Parameters

Parameter	Type	Default	Description
file_path	string	required	Path to the audio file to transcribe

Examples

Transcribe a voice message

{
  "file_path": "/path/to/voice message.m4a"
}

Transcribe an audio file

{
  "file_path": "recordings/meeting_2024.wav"
}

Requirements

Groq API key must be configured (GROQ_API_KEY environment variable)
Supported audio formats: mp3, wav, m4a, ogg, webm, flac

Notes

Transcription is performed using Groq's Whisper Large V3 model
The API provides fast transcription with a generous free tier
Maximum file size: 25MB
Supports multiple languages (auto-detection)

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

yaml

targets:
  - https://api.opensmartroute.ai/api/v1/registry/codemo1991-nanobot-webui-voice-transcribe/manifest   # or paste the manifest below

Manifest

An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.

codemo1991-nanobot-webui-voice-transcribe.ocm.jsonjson

{
  "ocm": "1",
  "id": "codemo1991-nanobot-webui-voice-transcribe",
  "kind": "skill",
  "name": "voice-transcribe",
  "description": "Transcribe voice/audio to text using Groq Whisper API",
  "publisher": "codemo1991",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "coding"
    ],
    "tags": [
      "skill-md",
      "voice",
      "audio",
      "transcription",
      "whisper",
      "speech",
      "to",
      "text",
      "github"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "Transcribe voice/audio to text using Groq Whisper API"
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "github",
      "repository": "https://github.com/codemo1991/nanobot-webui",
      "path": "nanobot/skills/voice-transcribe/SKILL.md",
      "ref": "7af2a2a150a682920f1f72a11abbe4f1f912dd5e",
      "url": "https://github.com/codemo1991/nanobot-webui/blob/7af2a2a150a682920f1f72a11abbe4f1f912dd5e/nanobot/skills/voice-transcribe/SKILL.md",
      "key": "codemo1991/nanobot-webui/nanobot/skills/voice-transcribe/SKILL.md"
    }
  },
  "instructions": "# Voice Transcription Skill\n\nReceive voice/audio files and transcribe them to text using Groq Whisper API.\n\n## When to Use\n\nUse `voice-transcribe` tool for:\n\n- **Voice message transcription** - Convert voice messages to text\n- **Audio file transcription** - Transcribe audio files (mp3, wav, m4a, etc.)\n- **Meeting recording transcription** - Convert meeting recordings to text\n\n## Usage\n\nThe `voice_transcribe` tool handles the entire workflow:\n\n1. Receives the audio file\n2. Calls Groq Whisper API for transcription\n3. Returns the transcribed text\n\n## Parameters\n\n| Parameter | Type   | Default | D",
  "cost": {
    "context_tokens": 333
  }
}

Fetch it by URL: GET /api/v1/registry/codemo1991-nanobot-webui-voice-transcribe/manifest?version=1.0.0

Reviews

Star ratings from people who tried it. One review per account; edit yours any time.

No reviews yet. Install it, try it, and be the first to rate it.