
Digital health clinical asr setup
Checks API access and speech stack setup for a clinical speech recognition benchmark
- Scripts
- None
- Platforms
- Claude Code, Codex, Cursor
- GitHub stars
- 4K
- Last commit
- 2 days ago
- License
- Apache-2.0
- Listing updated
- 1 day ago
Similar skills
About Digital health clinical asr setup
Digital health clinical asr setup is an open-source agent skill for health and science. It is available on Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose.
This skill is the first stage of a clinical speech recognition evaluation workflow. It walks the agent through confirming that an NVIDIA API key is exported, checking the Python version, and installing the Python client libraries into a virtual environment. It then runs a single round-trip test: a short clinical sentence is synthesized with a hosted text-to-speech voice, and the resulting audio is transcribed with a hosted speech recognition model to confirm the connection works.
The skill also requires the agent to present a data-flow disclosure before any text or audio is sent to external endpoints. It explains that clinical sentences and generated audio go to NVIDIA's hosted service, and that terms may be looked up on Merriam-Webster. Users are told that real patient data should not be used. An optional dictionary key can enable pronunciation lookups, and the skill describes an alternative path that needs no key.
The skill expects Python 3.10 or newer, an NVIDIA API key, and network access to the hosted endpoints. It points the user to the next skill in the sequence once the test succeeds.
When your agent uses it
Stage 1 of Clinical ASR Flywheel. Use when bootstrapping a cycle: NVCF+MW disclosure, NVIDIA_API_KEY check, deps install, TTS+ASR smoke test.
From the skill's SKILL.md. Your agent reads this description to decide when to load the skill.
What it can access
From a static check of its 6 files (39 KB) on GitHub on 17 November 2026. Nothing was run. Read the files before you install a skill: it can tell your agent to run anything its tools allow.
Check another skill before you install it.
Install
Copy the skill folder to ~/.claude/skills/digital-health-clinical-asr-setup to use it in all your projects:
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/NVIDIA/skills.git "$tmp" &&
mkdir -p ~/.claude/skills &&
rm -rf ~/.claude/skills/digital-health-clinical-asr-setup &&
cp -R "$tmp/skills/digital-health-clinical-asr-setup" ~/.claude/skills/digital-health-clinical-asr-setup &&
rm -rf "$tmp"For one project only, put the folder in .claude/skills/digital-health-clinical-asr-setup inside it instead.
Copy the skill folder to ~/.agents/skills/digital-health-clinical-asr-setup to use it in every repository:
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/NVIDIA/skills.git "$tmp" &&
mkdir -p ~/.agents/skills &&
rm -rf ~/.agents/skills/digital-health-clinical-asr-setup &&
cp -R "$tmp/skills/digital-health-clinical-asr-setup" ~/.agents/skills/digital-health-clinical-asr-setup &&
rm -rf "$tmp"For one repository only, put the folder in .agents/skills/digital-health-clinical-asr-setup inside it instead.
Copy the skill folder to ~/.cursor/skills/digital-health-clinical-asr-setup to use it in every project:
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/NVIDIA/skills.git "$tmp" &&
mkdir -p ~/.cursor/skills &&
rm -rf ~/.cursor/skills/digital-health-clinical-asr-setup &&
cp -R "$tmp/skills/digital-health-clinical-asr-setup" ~/.cursor/skills/digital-health-clinical-asr-setup &&
rm -rf "$tmp"For one project only, put the folder in .cursor/skills/digital-health-clinical-asr-setup inside it instead.
Run in a terminal (add --scope workspace to install it for the current workspace only):
gemini skills install https://github.com/NVIDIA/skills.git --path skills/digital-health-clinical-asr-setupOr copy the folder to ~/.gemini/skills/digital-health-clinical-asr-setup yourself.
For GitHub Copilot in VS Code, copy the skill folder to ~/.copilot/skills/digital-health-clinical-asr-setup:
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/NVIDIA/skills.git "$tmp" &&
mkdir -p ~/.copilot/skills &&
rm -rf ~/.copilot/skills/digital-health-clinical-asr-setup &&
cp -R "$tmp/skills/digital-health-clinical-asr-setup" ~/.copilot/skills/digital-health-clinical-asr-setup &&
rm -rf "$tmp"For one project only, put the folder in .github/skills/digital-health-clinical-asr-setup inside it instead.
Get the folder:
git clone --depth 1 https://github.com/NVIDIA/skills.gitThen copy skills/skills/digital-health-clinical-asr-setup into your agent's skills folder as digital-health-clinical-asr-setup. Agents that support SKILL.md read one folder per skill.
What it does
- API key verification
- Confirms the NVIDIA API key is set in the shell without printing its value.
- Python environment setup
- Creates a virtual environment and installs the speech client and data libraries.
- Hosted speech smoke test
- Synthesizes a clinical sentence and transcribes it to confirm the hosted stack responds.
- Outbound data disclosure
- Requires a summary of which external services receive text and audio before work begins.
- Optional pronunciation lookup
- Describes an optional dictionary lookup path that can be enabled with a key or skipped.
Good for
- Set up my environment for a clinical speech recognition benchmark
- Check that my NVIDIA API key can reach the hosted speech services
- Confirm text-to-speech and transcription work before building a clinical term set
- Install the Python packages needed for a speech recognition evaluation
Digital health clinical asr setup FAQ
What does this skill need before it runs?
It needs an NVIDIA API key exported in the shell and Python 3.10 or newer. An optional Merriam-Webster dictionary key can enable pronunciation lookups.
Does it install anything system-wide?
No. The skill states it performs read-only checks and only creates a local virtual environment for the Python packages.
What data leaves my machine?
Clinical sentences and generated audio are sent to NVIDIA's hosted service, and individual terms may be sent to Merriam-Webster. The skill says real patient data must not be used.
What comes after this skill?
The skill directs the user to the next stage, digital-health-clinical-asr-build, once the smoke test passes.
How do I install Digital health clinical asr setup in Claude Code?
Copy the skill folder from GitHub to ~/.claude/skills/digital-health-clinical-asr-setup to use it in all your projects, or to .claude/skills/digital-health-clinical-asr-setup in one project.
Does Digital health clinical asr setup run scripts?
No. It is instructions only, with no scripts. This comes from a static check of the files on GitHub; nothing was run. Read the files before you install it.
Which AI agents can use Digital health clinical asr setup?
Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose. Each reads skills in the SKILL.md format from its own folder; the install steps on this page list them.
What are the best alternatives to Digital health clinical asr setup?
The closest alternatives to Digital health clinical asr setup are Digital health clinical asr eval, Digital health clinical asr build, Digital health clinical asr finetune, Ambient healthcare agent with nemotron voice agent and Nv reason cxr.
Where this comes from
- Description: from the skill's own SKILL.md.
More from NVIDIA/skills

Runs an iterative NVIDIA TAO AOI loop that improves PCB defect-inspection models
- Open source
- 4K GitHub stars
- Computer vision

Runs an iterative DEFT loop that improves Cosmos3 bare OK/NG AOI inspection accuracy
- Open source
- 4K GitHub stars
- AI models and LLM tooling

Runs an iterative mining-based DEFT loop to improve Cosmos Reason traffic-video
- Open source
- 4K GitHub stars
- AI models and LLM tooling

Runs NVIDIA TAO Grounding DINO detection through an iterative data-mining and retraining
- Open source
- 4K GitHub stars
- Computer vision

Runs an iterative RT-DETR retraining loop for binary industrial defect detection
- Open source
- 4K GitHub stars
- Design and media

Runs an iterative retrain-and-evaluate loop to improve NVIDIA TAO CLIP image-text
- Open source
- 4K GitHub stars
- AI models and LLM tooling
