Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →graniet/whisper
OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params).
Passed 20 of 22 test cases with the skill, and 16 of 22 without it.
and 2 more in the full report
5 fixed15 passed either way1 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
I have a raw video file named clip.mp4. Before feeding the audio track to a speech recognition tool, I want to use ffmpeg to strip the video and extract a 16-bit little-endian PCM WAV file named audio.wav. What command line invocation accomplishes this?
| Checked | Without skill | With skill |
|---|---|---|
| The ffmpeg command uses the -vn option to disable video. | Passed | Passed |
| The ffmpeg command specifies -acodec pcm_s16le for the output codec. | Missed | Passed |
The instructions your model reads when the skill loads.
This skill is repo-local and stays inactive until explicitly activated.
When the original instructions refer to legacy tool names, use these Kheish mappings:
terminal => bashweb_extract => web_fetch, plus web_search when discovery is neededsearch_files => grep_search and glob_searchbrowser_* tools require a browser-capable surfaced tool or MCP; if none is available, use the closest available surface and say so explicitlyWhen the instructions mention local helper files, resolve them from ${KHEISH_SKILL_DIR}.
OpenAI's multilingual speech recognition model.
Use when:
Metrics:
Use alternatives instead:
test cases passed, vs 16 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.