Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Seeed-Projects/Seeed-Jetson-DevelopTool --skill whisper-realtime-sttgit clone --depth 1 https://github.com/Seeed-Projects/Seeed-Jetson-DevelopToolWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/seeed-projects/seeed-jetson-developtool/whisper-realtime-stt)<a href="https://agentmods.dev/skills/seeed-projects/seeed-jetson-developtool/whisper-realtime-stt"><img src="https://agentmods.dev/badge/skills/seeed-projects/seeed-jetson-developtool/whisper-realtime-stt/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/seeed-projects/seeed-jetson-developtool/whisper-realtime-stt"><img src="https://agentmods.dev/badge/skills/seeed-projects/seeed-jetson-developtool/whisper-realtime-stt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 38 Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
- medium Privilege Escalation · line 38 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 84 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00065 | $0.00800 |
| Opus 5 | $0.00032 | $0.00400 |
| Sonnet 5 | $0.00013 | $0.00160 |
| Haiku 4.5 | $0.00006 | $0.00080 |
Grade B, and why
whisper-realtime-stt scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo apt update && sudo apt install ffmpeg How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Real-Time Speech-to-Text with Whisper on Jetson Orin
Deploy Whisper on Jetson Orin for real-time speech-to-text processing directly on-device, eliminating network dependency and enhancing privacy. Uses a USB microphone for audio input.
Execution model
Run one phase at a time. After each phase:
- Relay all output to the user.
- If output contains
[STOP]→ stop immediately, consult the failure decision tree. - If output ends with
[OK]→ tell the user "Phase N complete" and proceed to the next phase.
Prerequisites
| Requirement | Detail |
|---|---|
| Jetson device | reComputer or other Jetson Orin-based device |
| Microphone | reSpeaker Mic Array v2.0 or other USB microphone |
| JetPack | With CUDA support |
| Network | Internet access for cloning repo and installing packages |
Phase 1 — Install dependencies (~5 min)
git clone https://github.com/LJ-Hao/Deploy-Whisper-on-NVIDIA-Jetson-Orin-for-Real-time-Speech-to-Text.git
cd Deploy-Whisper-on-NVIDIA-Jetson-Orin-for-Real-time-Speech-to-Text
pip install -r requirements.txt
sudo apt update && sudo apt install ffmpeg
Configure the microphone sample rate:
arecord -D hw:2,0 --dump-hw-params
[OK] when all packages install and ffmpeg is available. [STOP] if pip or apt install fails.
Phase 2 — Test environment (~1 min)
python test.py
Verify ffmpeg is installed:
ffmpeg -version
[OK] when test.py prints successful library import messages and ffmpeg -version shows version info. [STOP] if imports fail or ffmpeg is not found.
Phase 3 — Run real-time speech-to-text
python main.py
Speak into the microphone and observe real-time transcription output.
[OK] when transcription appears in the terminal as you speak. [STOP] if audio device errors or model loading fails.
Failure decision tree
| Symptom | Action |
|---|---|
pip install -r requirements.txt fails |
Check Python version ≥ 3.8. Try pip install --upgrade pip first. |
ffmpeg not found after install |
Run sudo apt install ffmpeg again. Verify with which ffmpeg. |
arecord — no soundcard found |
Check USB microphone connection. Run arecord -l to list devices. Adjust device ID (hw:X,0). |
test.py import errors |
Re-run pip install -r requirements.txt. Check for missing system libraries. |
main.py — CUDA out of memory |
Close other GPU processes. Use a smaller Whisper model variant. |
main.py — no audio input |
Verify microphone with arecord -D hw:2,0 -f S16_LE -r 16000 -d 5 test.wav. |
| Poor transcription accuracy | Ensure microphone sample rate is 16000 Hz. Reduce background noise. |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 96 lines · 65 tokens per session scan B aa514a4f81c5
whisper-realtime-stt is a skill published in the GitHub repository Seeed-Projects/Seeed-Jetson-DevelopTool (54 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 800 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
spark-environment-setup
Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.
spark-memory-thermal-ops
Manage unified memory and thermals during long-running ML jobs on NVIDIA DGX Spark. Use when planning memory headroom for a training run on GB10, when a job OOMs on unified memory, or when monitoring temperature and power during multi-hour training.
spark-training-gotchas
Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.
llama-cpp
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.
minicpm5-deploy-vllm-ascend
Deploy MiniCPM5-2B with vLLM on Huawei Ascend NPU using vLLM-Ascend. Use when the user mentions vLLM-Ascend, Ascend NPU, Huawei Ascend, CANN, torchnpu, davinci devices, or wants an OpenAI-compatible MiniCPM5 server on Ascend hardware.
amc-run-rtsp-calibration
Calibrate a new dataset from live RTSP camera streams via the AutoMagicCalib REST API. Use when the user provides RTSP URLs or asks to calibrate live cameras; VIOS records clips, AMC ingests them, then runs calibration.