skills.rest
Aadi-110i
Aadi-110iCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

elevenlabs-stt

Transcribe audio with ElevenLabs Scribe models including diarization, timestamps, and forced alignment.

Updated Jul 28, 2026
Search Tags:#subtitles#transcription#elevenlabs#speech-to-text#diarization#scribe#forced alignment
One-click install
npx skills add https://github.com/Aadi-110i/PEP-PROJECT --skill elevenlabs-stt-aadi-110i
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: elevenlabs-stt
Source: https://github.com/Aadi-110i/PEP-PROJECT/tree/main/skills/elevenlabs-stt
Command: npx skills add https://github.com/Aadi-110i/PEP-PROJECT --skill elevenlabs-stt-aadi-110i

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Converting audio recordings into accurate, structured text with speaker labels and precise timing is difficult to do manually, especially across many languages and long recordings. ## Core Features & Use Cases - Speech-to-Text Transcription: Transcribe audio with Scribe v1/v2 models at 98%+ accuracy across 90+ languages with automatic language detection. - Speaker Diarization & Audio Events: Identify who spoke when and tag non-speech events like laughter, applause, and music. - Forced Alignment: Align known text to audio for word-level and character-level timestamps, ideal for subtitles, lip-sync, and karaoke. - Use Case: Transcribe a recorded meeting with speaker identification, then feed the transcript into a captioning workflow to generate timed subtitles for the video. ## Quick Start Ask the assistant to transcribe an audio file URL using ElevenLabs STT with speaker diarization enabled.

Frequently Asked Questions about elevenlabs-stt

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I transcribe audio with ElevenLabs Scribe?▼

Run belt app run elevenlabs/stt with an input JSON containing the audio URL. The Scribe v2 model is used by default and returns a transcript with over 98% accuracy across 90+ languages.

How to get word-level timestamps from audio for subtitles?▼

Use the elevenlabs/forced-alignment app with the audio URL and the exact spoken text. It returns word-level and character-level start and end times suitable for subtitles, lip-sync, and karaoke.

Does ElevenLabs STT support speaker diarization?▼

Yes, set the diarize parameter to true in the input JSON to enable speaker identification. The output labels which speaker said each segment, which is useful for meetings and interviews.

What languages does ElevenLabs speech-to-text support?▼

Scribe models support over 90 languages including English, Spanish, French, German, Chinese, Japanese, Korean, Arabic, and Hindi. Leave the language_code field empty for automatic language detection.

What is the difference between Scribe v1 and Scribe v2?▼

Scribe v2 is the latest model with the highest accuracy and is the default choice. Scribe v1 is the stable, proven earlier version and remains available for workflows that depend on it.

Related Skills

Explore More Content & Communication Skills→
Pixazo-AIPixazo-AI

audio-extract-api

Extract audio tracks from video files as mp3 or m4a via the Pixazo API.

Official
Basic
NoizAINoizAI
526

video-translation

Translate and dub spoken audio in videos using subtitle files and timeline-based TTS.

Official
Intermediate
fikriaffikriaf

whisper

Convert spoken language into written text across multiple languages.

Community
Intermediate
eachlabseachlabs
28

eachlabs-voice-audio

Convert text to speech and transcribe audio with speaker diarization.

Official
Advanced