Which languages are supported for transcription?

The skill supports dozens of languages including English, French, German, Japanese, Chinese, Spanish, and Korean. You can use the list_languages tool to see the full set of supported codes.

Can I transcribe audio files stored on my local computer?

Yes, the skill supports local file paths for various formats including MP3, WAV, M4A, AAC, OGG, and FLAC using the ElevenLabs transcription engine.

Does transcribing audio cost API credits?

Yes, using the high-quality ElevenLabs Scribe v2 via the transcribe tool costs credits. However, the skill checks for cached versions first to save costs, and Plaud's built-in processing is available as a free alternative.

What is speaker diarization?

Speaker diarization is the process of partitioning an audio stream into homogeneous segments according to the speaker identity, allowing the transcript to show who said what.

How long does it take to process a recording?

ElevenLabs transcription typically takes 60-120 seconds. Plaud's built-in server-side processing is slower, usually taking between 2-5 minutes.

Plaud Transcription & Diarization

Name: Plaud Transcription & Diarization
Author: harshav167

byharshav167

0•

Productivity & Workflow

Transcribes audio recordings and local files with high-accuracy speaker diarization using ElevenLabs Scribe v2 or Plaud's built-in processing.

The Transcription skill empowers Claude to convert voice recordings into structured, speaker-labeled text by integrating Plaud AI and ElevenLabs Scribe v2. It provides a robust pipeline for handling both local audio files and cloud-hosted Plaud recordings, featuring an intelligent caching system to prevent redundant API costs. Whether you need high-fidelity transcripts for meetings, interviews, or voice memos, this skill manages the complex workflow of downloading, processing, and formatting diarized text while offering cost-estimation tools for bulk operations.

Key Features

010 GitHub stars

02High-fidelity transcription via ElevenLabs Scribe v2 with speaker diarization

03Cost-aware processing with built-in transcript caching (RustFS)

04Support for local audio files in various formats (MP3, WAV, M4A, etc.)

05Asynchronous Plaud server-side processing for free, lower-quality transcripts

06Multi-language support with automatic ISO language code handling

Use Cases

01Transcribing local voice memos to feed into downstream AI analysis or summarization

02Converting meeting recordings into speaker-labeled transcripts for documentation

03Managing bulk transcription tasks with cost-checks and progress monitoring

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add harshav167/plaud-plugin transcription

For use in Claude.ai and ChatGPT

Key Features

010 GitHub stars

02High-fidelity transcription via ElevenLabs Scribe v2 with speaker diarization

03Cost-aware processing with built-in transcript caching (RustFS)

04Support for local audio files in various formats (MP3, WAV, M4A, etc.)

05Asynchronous Plaud server-side processing for free, lower-quality transcripts

06Multi-language support with automatic ISO language code handling

Use Cases

01Transcribing local voice memos to feed into downstream AI analysis or summarization

02Converting meeting recordings into speaker-labeled transcripts for documentation

03Managing bulk transcription tasks with cost-checks and progress monitoring

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add harshav167/plaud-plugin transcription

For use in Claude.ai and ChatGPT