# openai-whisper-api

SkillBoss API Hub — Audio Transcription (STT) Transcribe an audio file via SkillBoss API Hub's /v1/pilot endpoint (type: stt), which automatically routes to the best available speech recognition model. Quick start

{baseDir}/scripts/transcribe.sh /path/to/audio.m4a
Defaults:
Model: auto-routed by SkillBoss API Hub
Output: <input>.txt

Useful flags

{baseDir}/scripts/transcribe.sh /path/to/audio.ogg --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
Note: --model is accepted for compatibility but ignored; SkillBoss API Hub auto-routes to the optimal STT model.

API key Set SKILLBOSS_API_KEY (SkillBoss API Hub unified key):

export SKILLBOSS_API_KEY=your_key_here

Or configure it in ~/.clawdbot/clawdbot.json: {

skills: {

"openai-whisper-api": {

apiKey: "SKILLBOSS_KEY_HERE"

} } }