Groq Whisper Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Groq Whisper Mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
MCP server for audio/video transcription via Groq-hosted Whisper. Word-level timestamps, automatic caching, cost estimation.
9x cheaper than OpenAI Whisper — same model, different API.
| Provider | Model | Cost/hour |
|---|---|---|
| Groq | whisper-large-v3-turbo | $0.04 |
| Groq | whisper-large-v3 | $0.111 |
| Groq | distil-whisper | $0.02 |
| OpenAI | whisper-1 | $0.36 |
git clone https://github.com/bis-code/groq-whisper-mcp.git
cd groq-whisper-mcp
python3 -m venv venv
venv/bin/pip install mcp openaiAdd to your project's .mcp.json:
{
"mcpServers": {
"whisper": {
"command": "/path/to/groq-whisper-mcp/venv/bin/python",
"args": ["-m", "server"],
"cwd": "/path/to/groq-whisper-mcp/src",
"env": {
"GROQ_API_KEY": "your-groq-api-key"
}
}
}
}transcribe_videoTranscribe a video file with word-level timestamps.
| Parameter | Type | Required | Description |
|---|---|---|---|
video_path | string | yes | Path to video file |
model | string | no | Whisper model (default: whisper-large-v3-turbo) |
force_retranscribe | boolean | no | Bypass cache (default: false) |
Returns full text, word-level timestamps [{word, start, end}], and duration. Results are cached per-project.
estimate_transcription_costEstimate cost before transcribing.
| Parameter | Type | Required | Description |
|---|---|---|---|
video_path | string | yes | Path to video file |
model | string | no | Whisper model (default: whisper-large-v3-turbo) |
Returns duration, estimated cost, and comparison with OpenAI pricing.
openai SDK, different base_url)whisper_words.json alongside the videoPYTHONPATH=src venv/bin/pytest tests/ -vMIT
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.