Agent skill · writing content · aiskillstore
stt
Transcribe audio to text using OpenAI Whisper through the verging.ai proxy API.
Why this skill is useful
Provides specific API commands and parameters for using the verging.ai speech-to-text service that the AI wouldn't reliably generate on its own.
What it needs
Requires verging.ai account access. About 1k tokens when loaded. Last updated 2026-08-07. 405 stars on the source repository.
What this skill does
Speech-to-Text — verging.ai Transcribe audio to text using OpenAI Whisper through the verging.ai proxy API. Authentication All requests require an API key in the Authorization header: Replace vrgskxxx with your verging.ai API key. You can generate one at https://verging.ai under your account settings. Endpoint Parameters Parameter Type Required Default Description ----------------- -------- ---------- ----------- ------------------------------------------------ file file Yes — Audio file to transcribe model string No whisper-1 STT model language string No — Language code (e.g. en, zh, ja) responseformat string No json Output format temperature float No — Sampling temperature (0–1) Supported Audio Formats mp3, mp4, mpeg, mpga, m4a, wav, webm File Size Limit Maximum file size: 25 MB Example Response text — Transcribed text content. language — Detected or specified language. duration — Audio duration in seconds. creditsconsumed — Credits deducted for this request. Credits Rate Minimum ------------------ --------- 1 credit / minute 1 credit Error Codes HTTP Status Error Code Description ------------- ------------ -------------------------------------------------- 400 — File exceeds 25 MB or unsupported audio format 402 40001 Insufficient credits 429 — Rate limit exceeded (check X-RateLimit-Reset) 502 — Upstream provider error 503 — Service unavailable or upstream timeout Error response format:
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aiskillstore/stt