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.
86
83%
Does it follow best practices?
Impact
94%
1.88xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Evaluation results
100%
3%Call Quality Analysis Tool
Call center diarization and speaker roles
Correct Python package
100%
100%
Correct model ID
100%
100%
Diarization enabled
100%
100%
Speaker role detection enabled
100%
100%
Multi-channel not used with speaker roles
100%
100%
Keyterms within limits
100%
100%
cloud_storage_url used
100%
100%
Request ID retrieval
100%
100%
Word-type filtering
100%
100%
Error handling: 401
100%
100%
Error handling: 422
100%
100%
Error handling: 429
50%
100%
82%
58%Podcast Subtitle Generator
JS package, source_url, additional_formats, no_verbatim
Correct JS package import
0%
100%
Correct package installed
0%
100%
Correct model ID
0%
100%
source_url used for YouTube
0%
100%
SRT additional format requested
0%
0%
TXT additional format requested
0%
0%
no_verbatim enabled
0%
100%
Raw response for request ID
50%
100%
API key from environment
100%
100%
Output files written
100%
100%
100%
69%Live Meeting Notes App
React real-time streaming, VAD, token security, status handling
React package used
0%
100%
Backend package used
0%
100%
Single-use token creation
25%
100%
API key server-side only
100%
100%
Token fetched from backend
100%
100%
CommitStrategy.VAD set
0%
100%
Active state checks both statuses
0%
100%
Correct model ID
0%
100%
Microphone echo cancellation
50%
100%
Microphone noise suppression
50%
100%
Partial transcript handler
50%
100%
- Repository
- elevenlabs/skills
- Commit
df1e602
- Evaluated
- Agent
- Claude Code
- Model
- Claude Sonnet 4.6
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.