Content Creation & Writing

Speech To Text

The skill transcribes spoken audio into accurate, timestamped text using ElevenLabs Scribe v2 and Whisper models, providing speaker diarization and event tagging. It supports multiple languages and can translate content on the fly, making it ideal for meeting minutes, podcast transcripts, subtitles, and voice notes. Clients such as content creators, corporate teams, and accessibility services benefit from reliable, automated transcription and translation.

Publisher / source
halt-catch-fire/mutiny (found on skills.sh)
Upstream record
halt-catch-fire/mutiny
Version
Version 1
Published
Publication review
Approved for publication
Content fingerprint
fb34e895146bcca385b99f457cef1927b2da2e1ed9c736c935263b2926c9de74