Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
SkillScore76Maintained
Automatic
◆AI Engineer pack
Last verified 9/2/2026
What it changes
Passed 19 of 25 test cases with the skill, and 9 of 25 without it.
Without skill36%
With skill76%
Checks it passed that the model alone missed
The output gives the transcript text.
The output contains the transcript text.
The response lists concrete action items.
and 15 more in the full report
10 fixed9 passed either way6 still failing0 broke
Pass-rate lift
+40 pp
Tokens
-11%
Agent turns
0%
Response time
-19%
Model gemini-3.6-flashMeasured 9/2/2026v2 · latest is v319 of 25 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
See it in action
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 10
Prompt
Please submit the legal deposition audio file `depo_witness_03.wav` to Atlas Cloud speech-to-text to obtain the transcript and explicit follow-up action notes.
What was checked, without and with the skill
Checked
Without skill
With skill
The output contains the generated transcript text.
Missed
Passed
The output specifies concrete action notes.
Missed
Passed
case-09 · gemini-3.6-flash · 9/2/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md33 lines2 filesincludes scripts
Openai-whisper-api
Purpose
Transcribe audio via OpenAI Whisper, Atlas Cloud, or MuAPI speech-to-text APIs.
Routing
Use when: Use when the user asks to transcribe audio through OpenAI Whisper, Atlas Cloud, or MuAPI speech-to-text.
Do not use when: Do not use when the request is asking for planning documents, high-level strategy, or non-executable discussion; use the relevant planning or design workflow instead.
Outputs: Outcome from Openai-whisper-api: task-specific result plus concrete action notes.
Success criteria: Returns concrete actions and decisions matching the requested task, with no fabricated tool-side behavior.
Trigger Examples
Positive
Use the openai-whisper-api skill for this request.
Help me with openai-whisper-api.
Use when the user asks to transcribe audio through OpenAI Whisper, Atlas Cloud, or MuAPI speech-to-text.
Openai-whisper-api: provide an actionable result.
Negative
Do not use when the request is asking for planning documents, high-level strategy, or non-executable discussion; use the relevant planning or design workflow instead.
Do not use openai-whisper-api for unrelated requests.
This request is outside openai-whisper-api scope.
This is conceptual discussion only; no tool workflow is needed.
Runtime Prompt
Current runtime prompt length: 1683 characters.
Runtime prompt is defined directly in ../openai-whisper-api.json.