Can this skill identify different speakers in a recording?

Yes, it includes speaker diarization capabilities that can identify and distinguish between up to 32 different speakers in a single audio file.

How does this skill handle background noise like laughter?

It features audio event detection which can automatically identify and tag non-speech sounds such as laughter and applause during the transcription process.

What languages are supported by the ElevenLabs STT skill?

The skill supports 99 languages using the Scribe v1 model, including English, Spanish, French, Japanese, Mandarin, and many others with varying levels of accuracy.

Does this skill require the Vercel AI SDK to function?

No, while it provides excellent Vercel AI SDK integration, it also includes scripts for direct API access via curl and standard TypeScript/Python templates.

What are the file size and duration limits for transcription?

The skill supports audio and video files up to 3 GB in size and up to 10 hours in duration, with specialized handling for files longer than 8 minutes.

ElevenLabs Speech-to-Text Integration

Name: ElevenLabs Speech-to-Text Integration
Author: vanman2024

byvanman2024

データサイエンスとML

Integrates ElevenLabs Scribe v1 for high-accuracy speech-to-text transcription across 99 languages with speaker diarization.

概要

This skill empowers developers to implement ElevenLabs Scribe v1 Speech-to-Text capabilities directly within their projects, featuring support for 99 languages and advanced speaker diarization for up to 32 participants. It provides a comprehensive toolkit including Vercel AI SDK templates, shell scripts for batch processing, and word-level timestamping. Whether you are building subtitle generators, meeting transcription tools, or multi-language accessibility features, this skill offers the standardized patterns and automation needed to handle complex audio and video transcription workflows efficiently.

主な機能

Multi-language support for 99 languages with state-of-the-art Scribe v1 accuracy
Advanced speaker diarization for identifying and tracking up to 32 individual speakers
Seamless Vercel AI SDK integration with TypeScript and Python templates
Support for 15+ audio and video formats including MP3, WAV, MP4, and WebM
0 GitHub stars
Precise word-level timestamps and automated audio event detection

ユースケース

Building automated meeting transcription and speaker identification tools
Creating multi-language subtitle generators for video content repositories
Developing voice-driven accessibility features using high-accuracy speech-to-text

概要

主な機能

Multi-language support for 99 languages with state-of-the-art Scribe v1 accuracy
Advanced speaker diarization for identifying and tracking up to 32 individual speakers
Seamless Vercel AI SDK integration with TypeScript and Python templates
Support for 15+ audio and video formats including MP3, WAV, MP4, and WebM
0 GitHub stars
Precise word-level timestamps and automated audio event detection

ユースケース

Building automated meeting transcription and speaker identification tools
Creating multi-language subtitle generators for video content repositories
Developing voice-driven accessibility features using high-accuracy speech-to-text