Elevenlabs Transcribe

What This Skill Does

The Eleven Labs Speech-to-Text skill converts audio to text with high accuracy, supporting over 90 languages. It features speaker diarization and realtime streaming capabilities, making it ideal for transcription services, meeting recording analysis, and integration into voice-enabled applications.

When to Use

Transcribe meeting recordings with speaker identification. Convert podcast audio to text for accessibility. Create subtitles for video content. Analyze customer service call recordings. Enable voice control in applications. Stream live audio and transcribe in real-time.

Key Features

Supports 90+ languages. Features speaker diarization. Offers realtime streaming transcription. Provides options for JSON output with timestamps. Identifies audio events like laughter and music. Can suppress status messages for agent integration.

Manual Installation

Manual installation View Full Skill Content The complete markdown content that gets installed Eleven Labs Speech-to-Text

Official Eleven Labs skill for speech-to-text transcription.

Convert audio to text with state-of-the-art accuracy. Supports 90+ languages, speaker diarization, and realtime streaming.

Prerequisites

ffmpeg installed (brew install ffmpeg on mac OS) ELEVENLABS_API_KEY environment variable set Python 3.8+ (dependencies auto-install on first run)

Usage

{base Dir}/scripts/transcribe.sh <audio_file> [options] {base Dir}/scripts/transcribe.sh --url <stream_url> [options] {base Dir}/scripts/transcribe.sh --mic [options]

Examples

Batch Transcription

Transcribe a local audio file:

{base Dir}/scripts/transcribe.sh recording.mp3

With speaker identification:

{base Dir}/scripts/transcribe.sh meeting.mp3 --diarize

Get full JSON response with timestamps:

{base Dir}/scripts/transcribe.sh interview.wav --diarize --json

Realtime Streaming

Stream from a URL (e.g., live radio, podcast):

{base Dir}/scripts/transcribe.sh --url https://npr-ice.streamguys1.com/live.mp3

Transcribe from microphone:

{base Dir}/scripts/transcribe.sh --mic

Stream a local file in realtime (useful for testing):

{base Dir}/scripts/transcribe.sh audio.mp3 --realtime

Quiet Mode for Agents

Suppress status messages on stderr:

{base Dir}/scripts/transcribe.sh --mic --quiet

Options

Output Format

Text Mode (default)

Plain text transcription:

The quick brown fox jumps over the lazy dog.

JSON Mode (--json)

{ "text": "The quick brown fox jumps over the lazy dog.", "language_code": "eng", "language_probability": 0.98, "words": [ {"text": "The", "start": 0.0, "end": 0.15, "type": "word", "speaker_id": "speaker_0"} ] }

Realtime Mode

Final transcripts print as they're committed. With --partials:

[partial] The quick [partial] The quick brown fox The quick brown fox jumps over the lazy dog.

Supported Formats

Audio: MP3, WAV, M4A, FLAC, OGG, Web M, AAC, AIFF, Opus Video: MP4, AVI, MKV, MOV, WMV, FLV, Web M, MPEG, 3GPP

Limits: Up to 3GB file size, 10 hours duration

Error Handling

The script exits with non-zero status on errors:

Missing API key: Set ELEVENLABS_API_KEY environment variable File not found: Check the file path exists Missing ffmpeg: Install with your package manager API errors: Check API key validity and rate limits

When to Use Each Mode

Official Eleven Labs skill for speech-to-text transcription.

Convert audio to text with state-of-the-art accuracy. Supports 90+ languages, speaker diarization, and realtime streaming.