Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

OpenAI Whisper API (curl) — measured AI agent skill | DecimalAI

understudy-ai/openai-whisper-api

NewSkillScoreMaintained

Transcribe audio via OpenAI Audio Transcriptions API (Whisper).

design-mediaby understudy-ai

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

AI Engineer pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/understudy-ai-openai-whisper-api/SKILL.md

decimalai skills pull understudy-ai-openai-whisper-api --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/understudy-ai-openai-whisper-api/SKILL.md https://app.decimal.ai/s/understudy-ai-openai-whisper-api/SKILL.md

Raw file: /s/understudy-ai-openai-whisper-api/SKILL.md ↗ · machine-readable summary at /s/understudy-ai-openai-whisper-api.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

24 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 1h ago

Yes — +50% lift-34% tokens0% turns92% of whole cases pass with skill (22/24)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-21	✗→✓	▲ Improved	-43%	0%
case-01	✗→✓	▲ Improved	-30%	0%
case-19	✗→✓	▲ Improved	-47%	0%
case-07	✗→✓	▲ Improved	-37%	0%
case-20	✗→✓	▲ Improved	-37%	0%

Showing 5 of 24 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

understudy-ai / understudy

skills/openai-whisper-api/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1Bundled 1 file · scripts

Skill contents

scripts/

SKILL.md

OpenAI Whisper API (curl)

Transcribe an audio file via OpenAI’s /v1/audio/transcriptions endpoint.

Quick start

bash
{baseDir}/scripts/transcribe.sh /path/to/audio.m4a

Defaults:

Model: whisper-1
Output: <input>.txt

Useful flags

bash
{baseDir}/scripts/transcribe.sh /path/to/audio.ogg --model whisper-1 --out /tmp/transcript.txt
{baseDir}/scripts/transcribe.sh /path/to/audio.m4a --language en
{baseDir}/scripts/transcribe.sh /path/to/audio.m4a --prompt "Speaker names: Peter, Daniel"
{baseDir}/scripts/transcribe.sh /path/to/audio.m4a --json --out /tmp/transcript.json

API key

Set OPENAI_API_KEY, or configure it in ~/.understudy/config.json5:

json5
{
  skills: {
    "openai-whisper-api": {
      apiKey: "OPENAI_KEY_HERE",
    },
  },
}

Want to see if understudy-ai/openai-whisper-api would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.