Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →vellum-ai/transcribe
Transcribe audio and video files using the configured speech-to-text provider
Passed 15 of 19 test cases with the skill, and 10 of 19 without it.
and 3 more in the full report
6 fixed11 passed either way4 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
To select OpenAI Whisper as the active engine in the system configuration settings, which config key path should be set?
| Checked | Without skill | With skill |
|---|---|---|
| Identifies `services.stt` under Settings as the configuration location. | Missed | Passed |
The instructions your model reads when the skill loads.
Transcribe audio and video files using the configured speech-to-text provider. Supports multiple STT providers including OpenAI Whisper, Deepgram, and Google Gemini — the active provider is selected in Settings under Speech-to-Text (services.stt).
file_path (absolute path to a local audio or video file) to transcribe.services.stt) is shared between transcription and telephony call paths.When adding or modifying an STT provider, follow the onboarding checklist at assistant/docs/stt-provider-onboarding.md. That document covers the daemon catalog, config schema, adapter wiring, client catalog parity, and required tests.
test cases passed, vs 10 / 19 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.