Free Groq Voice Recognition

FREE voice recognition using Groq's complimentary Whisper API. Transcribe audio messages to text in 50+ languages at no cost. Perfect for voice-to-text autom...

Security Scan

The skill appears to implement Groq Whisper transcription, but its published metadata omits required credentials and binaries (GROQ_API_KEY, jq) and contains a few misleading/inconsistent statements — these mismatches warrant caution before installing.

Purpose & Capability

The skill's purpose (Groq Whisper transcription) is consistent with the included transcribe.sh and SKILL.md. However the registry metadata declares no required environment variables or binaries while the runtime files clearly require GROQ_API_KEY and the jq binary (and the README mentions a Bash shell). This mismatch between declared requirements and actual needs is an incoherence.

Instruction Scope

SKILL.md and transcribe.sh stay within transcription scope (calling Groq's /audio/transcriptions endpoint and processing audio files). The docs advise storing the API key in a local TOOLS.md and support batch processing of audio files; these are reasonable for the task but the instructions don't specify secure handling of the key and implicitly allow processing arbitrary files in a folder, which increases risk if misused.

Install Mechanism

No install spec is provided (instruction-only plus a small shell script), so nothing is downloaded or executed during install. That's low-risk. Note: the script depends on external tools (curl, jq, bash), but the metadata didn't declare those dependencies.

Credentials

Functionality reasonably requires a single API credential (GROQ_API_KEY) and optionally a GROQ_PROXY setting — that is proportionate. The problem is the skill registry declares no required env vars or primary credential, which is misleading and prevents platform-level controls or warning about secret use.

Persistence & Privilege

The skill does not request always:true, does not modify other skills, and has no install-time persistence. It only expects the operator to provide an API key/config locally; no elevated platform privileges are requested.

What to consider before installing

This skill's behavior (curl to api.groq.com with Authorization) matches its claimed purpose, but the package metadata is incomplete. Before installing: 1) Treat your GROQ_API_KEY as a secret — do not paste it into shared or public files; prefer storing it as an environment variable or in a secure vault rather than plaintext TOOLS.md. 2) Ensure your environment has curl, jq and bash available (transcribe.sh uses jq to extract .text). 3) Verify Groq's free-tier terms on https://console.groq.com/ to confirm the "100% free, no limits" claim. 4) If you need auditing or least privilege, ask the publisher to update the registry metadata to declare GROQ_API_KEY as a required credential and list required binaries (jq, curl). 5) If you are in a restricted network and must use a proxy, confirm the proxy address and understand that traffic (audio and API key in Authorization header) will be sent to api.groq.com. 6) If you want higher confidence, request the author to provide provenance (homepage or source repo) and a signed update to the metadata; without that, treat the skill as functional but inconsistently documented.

Overview

100% FREE voice recognition powered by Groq's complimentary Whisper API (whisper-large-v3 model). No credit card required, no usage limits.

Convert audio messages, voice notes, and recordings to text in 50+ languages. Perfect for:

• 🎙️ Voice message transcription
• 📝 Meeting notes
• ♿ Accessibility features
• 🤖 Voice-controlled automation

Cost: $0.00

• ✅ Completely free Groq API tier
• ✅ No credit card needed
• ✅ No monthly fees
• ✅ Generous rate limits
• ✅ Whisper-large-v3 model (most accurate)

Setup

1. Get Your FREE Groq API Key

1. Visit https://console.groq.com/
2. Sign up for free (takes 30 seconds)
3. Navigate to API Keys
4. Create a new API key
5. Copy the key

That's it! No payment required.

2. Configure Proxy (If in Restricted Regions)

Groq API may require a proxy in certain regions (e.g., mainland China).

Add to your TOOLS.md:

### Proxy Settings
- HTTP Proxy: http://127.0.0.1:7890

### Voice Recognition (FREE Groq Whisper)
- API Key: gsk_your_key_here
- Model: whisper-large-v3
- Language: zh (or your preferred language)
- Requires Proxy: Yes (if in restricted region)

3. Test the Skill

Send a voice message and ask me to transcribe it!

Usage Examples

Basic Transcription:

User: [sends voice message]
You: You said: "你好，这是一条测试消息"

With Language Hint:

User: 识别这段英文语音
You: [automatically uses language=en]

Batch Processing:

User: 帮我识别这个文件夹里所有的语音文件
You: [processes all .ogg/.mp3/.wav files]

Supported Languages

• 🇨🇳 Chinese (zh) - Mandarin, Cantonese
• 🇺🇸 English (en) - US, UK, Australian
• 🇯🇵 Japanese (ja)
• 🇰🇷 Korean (ko)
• 🇫🇷 French (fr)
• 🇩🇪 German (de)
• 🇪🇸 Spanish (es)
• 🇮🇹 Italian (it)
• 🇵🇹 Portuguese (pt)
• 🇷🇺 Russian (ru)
• ... and 40+ more

Technical Details

API Endpoint:

https://api.groq.com/openai/v1/audio/transcriptions

Model: whisper-large-v3 (OpenAI's most accurate model)

Supported Formats:

• OGG/OPUS (Feishu, Telegram default)
• MP3
• WAV
• M4A
• WebM

Proxy Requirements:

• Use HTTP proxy (not SOCKS5)
• Default: http://127.0.0.1:7890

Troubleshooting

❌ "Forbidden" Error:

• Check API key is valid
• Ensure proxy is configured (if in restricted region)
• Try HTTP proxy instead of SOCKS5

❌ "File Not Found":

• Check file path is absolute
• Ensure file exists

❌ Slow Response:

• Check proxy speed
• Groq API is usually fast (< 1s for short audio)

Privacy & Security

• ✅ Audio processed by Groq's API (not stored permanently)
• ✅ API key stored locally in your TOOLS.md
• ✅ No data sent to third parties
• ✅ Open-source and auditable

Why Groq?

FREE vs Paid Alternatives:

Service	Cost	Accuracy	Speed
Groq (FREE)	$0	⭐⭐⭐⭐⭐	⚡⚡⚡⚡⚡
OpenAI Whisper	$0.006/min	⭐⭐⭐⭐⭐	⚡⚡⚡
Google Speech	$0.006/min	⭐⭐⭐⭐	⚡⚡⚡⚡
AWS Transcribe	$0.024/min	⭐⭐⭐⭐	⚡⚡⚡

Groq's free tier offers:

• Same Whisper-large-v3 model as OpenAI
• Faster inference (Groq's LPU chip)
• No usage limits (fair use policy)
• No credit card required

Contributing

Want to improve this skill?

• Fork on ClawHub
• Submit improvements
• Share with the community

License

MIT - Free to use, modify, and distribute.

---

Enjoy FREE voice recognition! 🎉

No more paying for transcription services. Groq's complimentary API makes professional-grade speech-to-text accessible to everyone.