Transcribe audio files using ElevenLabs Speech-to-Text (Scribe v2).
Real data. Real impact.
Emerging
Developers
Per week
Open source
Skills give you superpowers. Install in 30 seconds.
Transcribe audio files using ElevenLabs' Scribe v2 model. Supports 90+ languages with speaker diarization.
# Basic transcription {baseDir}/scripts/transcribe.sh /path/to/audio.mp3With 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
| Flag | Description |
|---|---|
| Identify different speakers |
| ISO language code (e.g., en, pt, es) |
| Output full JSON with word timestamps |
| Tag audio events (laughter, music, etc.) |
All major audio/video formats: mp3, m4a, wav, ogg, webm, mp4, etc.
Set
ELEVENLABS_API_KEY{ skills: { entries: { "elevenlabs-stt": { apiKey: "sk_..." } } } }
# Transcribe a WhatsApp voice note {baseDir}/scripts/transcribe.sh ~/Downloads/voice_note.oggMeeting 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
No automatic installation available. Please visit the source repository for installation instructions.
View Installation Instructions
4,600+ AI skills, agents & workflows. Install in 60 seconds. Part of the Torly.ai family.
© 2026 Torly.ai. All rights reserved.