speech-to-text
Transcribe audio to text using ElevenLabs Scribe v2. Use when converting audio/video to text, generating subtitles, transcribing meetings, or processing spoken content.
88
—
Does it follow best practices?
Impact
88%
1.33xAverage score across 3 eval scenarios
—
The risk profile of this skill
Evaluation results
94%
22%Legal Dictation Assistant
React live transcription component with secure backend token
React hook package
0%
100%
Server-side package
100%
100%
API key absent from frontend
100%
100%
Token creation method
100%
100%
VAD commit strategy
50%
100%
Dual status check
0%
40%
Partial transcript for live display
100%
100%
Committed transcript persistence
100%
100%
Microphone audio options
100%
100%
Compatible option pairing
100%
100%
Zero-retention logging
100%
100%
80%
30%Live Audio Transcription Tool for Production Pipeline
Node.js real-time streaming transcription script
Correct npm package
0%
100%
Realtime model ID
100%
100%
PCM audio format
100%
100%
Chunk size
0%
100%
Manual commit interval
0%
0%
Partial for display only
100%
100%
Committed transcript saved
100%
100%
noVerbatim enabled
100%
100%
ElevenLabsClient import
0%
100%
RealtimeEvents import
0%
0%
invalid_request handled
100%
100%
previous_text sent
0%
0%
92%
16%Meeting Transcript Processor
Meeting transcription with speaker diarization
Correct model_id
0%
100%
Diarization enabled
100%
100%
Keyterms parameter used
100%
100%
Word-level timestamps
100%
100%
Word type filtering
66%
100%
no_verbatim enabled
100%
100%
language_code set
50%
0%
Speaker ID grouping
100%
100%
API key from environment
100%
100%
requirements.txt present
25%
100%
- Repository
- elevenlabs/skills
- Commit
9edcbd4
- Evaluated
- Agent
- Claude Code
- Model
- Claude Sonnet 4.6
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.