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
83%
Does it follow best practices?
Impact
100%
1.81xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Evaluation results
100%
70%Customer Support Call Analyzer
JS batch transcription with speaker roles
Correct JS package
0%
100%
No deprecated package
0%
100%
Correct model ID
0%
100%
Diarization enabled
100%
100%
Speaker role detection
0%
100%
No multi-channel conflict
100%
100%
Keyterms provided
0%
100%
ElevenLabsClient import
0%
100%
No hardcoded API key
100%
100%
100%
53%Live Dictation Widget for a Medical Notes App
React real-time mic transcription with VAD and status
React hook import
0%
100%
CommitStrategy import
0%
100%
VAD commit strategy
0%
100%
Dual-state active check
0%
100%
Token from backend
66%
100%
No API key on client
100%
100%
Correct realtime model
100%
100%
Keyterms included
50%
100%
Committed transcript accumulation
100%
100%
Partial transcript display
100%
100%
100%
12%Podcast Chapter Generator
Python server-side realtime streaming with audio chunking
Correct realtime model
100%
100%
PCM 16-bit format
100%
100%
16kHz sample rate
100%
100%
Mono conversion
100%
100%
32000-byte chunk size
0%
100%
no_verbatim enabled
100%
100%
Timestamps requested
100%
100%
Keyterms provided
100%
100%
Manual commit used
75%
100%
Correct Python package
100%
100%
No API key hardcoded
100%
100%
- Repository
- elevenlabs/skills
- Commit
2869274
- 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.