speech-vlm

speech-vlm is a skill for Claude Code, Codex from Seeed-Projects/Seeed-Jetson-DevelopTool. It costs 63 tokens per session (1,246 once invoked), scanned B, original, MIT.

A setup guide for voice-controlled visual understanding on selected reComputer Jetson devices. It combines a visual-language model, speech-to-text to transcribe speech, and text-to-speech to produce spoken replies.

In plain words
What is it for?
Installing the audio and model dependencies, connecting a microphone and speaker, receiving camera video, transcribing speech, and speaking responses.
Why use it?
It connects camera input and spoken interaction so the device can interpret scenes and respond by voice.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Installing the audio and model dependencies, connecting a microphone and speaker, receiving camera video, transcribing speech, and speaking responses.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/seeed-projects/seeed-jetson-developtool/speech-vlm
Install

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.

Any agent
npx skills add Seeed-Projects/Seeed-Jetson-DevelopTool --skill speech-vlm
Clone the repo
git clone --depth 1 https://github.com/Seeed-Projects/Seeed-Jetson-DevelopTool

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for speech-vlm

README.md
[![agentmods](https://agentmods.dev/badge/skills/seeed-projects/seeed-jetson-developtool/speech-vlm.svg)](https://agentmods.dev/skills/seeed-projects/seeed-jetson-developtool/speech-vlm)
Your own site
<a href="https://agentmods.dev/skills/seeed-projects/seeed-jetson-developtool/speech-vlm"><img src="https://agentmods.dev/badge/skills/seeed-projects/seeed-jetson-developtool/speech-vlm.svg" alt="Measured on agentmods" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,246 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 15 findings, up to medium

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 →

  • medium Privilege Escalation · line 35
    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 41
    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 42
    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 43
    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 81
    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 90
    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 99
    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 104
    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 117
    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 131
    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 143
    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 145
    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 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 155
    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 160
    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.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00063 $0.01246
Opus 5 $0.00032 $0.00623
Sonnet 5 $0.00013 $0.00249
Haiku 4.5 $0.00006 $0.00125

Measured 5d ago against content hash 0f9ee66f16e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

speech-vlm 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 5d 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-get install nvidia-jetpack
seeed_jetson_develop/skills/openclaw/speech-vlm/SKILL.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run VLM with Speech Interaction

Execution model

Run one phase at a time. After each phase, verify the expected result before continuing.

  • If a phase succeeds → print [OK] and move to the next phase.
  • If a phase fails → print [STOP], consult the failure decision tree, and ask the user before retrying.

Phase 1 — Verify prerequisites

Required hardware:

  • reComputer Jetson AGX Orin 64G or Orin NX 16G (16GB+ memory)
  • USB driver-free speaker microphone
  • IP camera with RTSP output (or use NVStreamer for local video)
# Check JetPack 6 and CUDA
cat /etc/nv_tegra_release
nvcc --version
# Check available memory
free -h

Expected: JetPack 6.x installed; CUDA available; 16GB+ RAM.

Phase 2 — Initialize system environment

# Ensure nvidia-jetpack is fully installed
sudo apt-get install nvidia-jetpack

# Install system dependencies
sudo apt-get install libportaudio2 libportaudiocpp0 portaudio19-dev

# Install Python packages
sudo pip3 install pyaudio playsound subprocess wave keyboard
sudo pip3 --upgrade setuptools
sudo pip3 install sudachipy==0.5.2

Verify audio devices are working and network is stable:

arecord -l   # List recording devices
aplay -l     # List playback devices
ping -c 2 8.8.8.8

Expected: Audio devices listed; network reachable.

Phase 3 — Install VLM

Follow the NVIDIA Jetson VLM installation guide. Ensure you can perform text-based inference with VLM before proceeding.

Reference: Run VLM on reComputer

Phase 4 — Install PyTorch and Torchaudio

Install PyTorch, Torchaudio, and Torchvision matching your JetPack version.

Reference: PyTorch installation for Jetson

# Verify PyTorch with CUDA
python3 -c "import torch; print(torch.cuda.is_available())"

Expected: True

Phase 5 — Install Speech_vlm (SenseVoice)

Read the full file on GitHub · 165 lines

Files

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.

Changes

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.

  1. 5d ago First seen · 165 lines · 63 tokens per session scan B 0f9ee66f16e0

Subscribe to this mod's changes

speech-vlm is a skill published in the GitHub repository Seeed-Projects/Seeed-Jetson-DevelopTool (54 stars, last pushed yesterday), licensed MIT. It adds 63 tokens to every session and 1,246 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.

Related

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.

wshobson/agents · 76 tokens

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.

wshobson/agents · 59 tokens

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.

wshobson/agents · 63 tokens

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.

davila7/claude-code-templates · 76 tokens

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.

NVIDIA/skills · 59 tokens

amc-run-video-calibration

Calibrates pre-recorded cam.mp4 datasets through the AutoMagicCalib REST API. Use for user-supplied local MP4s; route live RTSP streams to amc-run-rtsp-calibration.

NVIDIA/skills · 57 tokens