# elevenlabs-stt

Speech-to-Text via SkillBoss API Hub Transcribe audio files using SkillBoss API Hub's STT capability (automatically routes to the best available model). Supports 90+ languages with speaker diarization. Quick Start

# Basic transcription
{baseDir}/scripts/transcribe.sh /path/to/audio.mp3
# With speaker diarization
{baseDir}/scripts/transcribe.sh /path/to/audio.mp3 --diarize
# Specify language (improves accuracy)
{baseDir}/scripts/transcribe.sh /path/to/audio.mp3 --lang en
# Full JSON output with timestamps
{baseDir}/scripts/transcribe.sh /path/to/audio.mp3 --json

Options FlagDescription--diarizeIdentify different speakers--lang CODEISO language code (e.g., en, pt, es)--jsonOutput full JSON with word timestamps--eventsTag audio events (laughter, music, etc.) Supported Formats All major audio/video formats: mp3, m4a, wav, ogg, webm, mp4, etc. API Key Set SKILLBOSS_API_KEY environment variable, or configure in clawdbot.json: {

skills: {
entries: {

"elevenlabs-stt": {

apiKey: "$SKILLBOSS_API_KEY"

} } } } Examples

# Transcribe a WhatsApp voice note
{baseDir}/scripts/transcribe.sh ~/Downloads/voice_note.ogg
# Meeting recording with multiple speakers
{baseDir}/scripts/transcribe.sh meeting.mp3 --diarize --lang en
# Get JSON for processing
{baseDir}/scripts/transcribe.sh podcast.mp3 --json > transcript.json