Groq Whisper

通过 scripts/transcribe.sh 调用 Groq 的 whisper-large-v3 云端语音转文本接口，把 ogg、mp3、wav、m4a、webm、flac 等音频文件转写为文本；需 curl、jq 和 Groq API 密钥，可选指定语言，默认英语，无需本地模型或格式转换。

directorvector

热度 51.52

最近更新 2026-05-11 17:41:28

分类：效率依赖：代码执行 / 读写文件 / 第三方 API应用场景：文件转换

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add groq-whisper

Metadata

name: groq-whisper
description: Transcribe audio files using Groq's Whisper API (whisper-large-v3). Fast cloud-based speech-to-text with no local model required. Use when receiving voice messages, audio files, or any speech that needs transcription. Supports all major audio formats (ogg, mp3, wav, m4a, webm, flac).
author: DirectorVector
homepage: https://github.com/DirectorVector
metadata: {"openclaw":{"requires":{"bins":["curl","jq"]},"env":[{"name":"GROQ_API_KEY","description":"Groq API key. Alternatively store in ~/.config/groq/credentials.json as {\"api_key\":\"gsk_...\"}.","required":false}]}}

Groq Whisper

Cloud speech-to-text via Groq's Whisper API. No local model, no GPU, no fan spin.

Setup

Get a free API key at console.groq.com

Store it:

mkdir -p ~/.config/groq
echo '{"api_key":"gsk_your_key_here"}' > ~/.config/groq/credentials.json
chmod 600 ~/.config/groq/credentials.json

Or set GROQ_API_KEY env var.

Usage

# Transcribe an audio file
{baseDir}/scripts/transcribe.sh /path/to/audio.ogg

# Specify language (default: en)
{baseDir}/scripts/transcribe.sh /path/to/audio.ogg es

When to use

Call this script whenever you receive an audio/voice message attachment. Pass the file path directly — Groq handles ogg, mp3, wav, m4a, webm, and flac natively. No format conversion needed.

Details

Model: whisper-large-v3 (best accuracy)
Speed: Faster than real-time (typically <2s for a 5-minute clip)
Cost: Free tier available, no credit card required
Privacy: Groq does not retain input data or train on it
Requires: curl, jq, Groq API key