Elevenlabs Transcribe
Transcribe audio & video files with speaker diarization using ElevenLabs API
What You Can Do
You can transcribe audio and video files into accurate text with automatic speaker diarization (identifying who said what), support for 32+ languages, and detection of audio events like background noise or music. The skill accepts flexible parameters for output formatting, custom terminology, and speaker count optimization, making it ideal for podcasts, interviews, meetings, lectures, and multilingual content.
Features
automatically identifies and labels different speakers in audio files
transcribes 32+ languages with ISO-639 language code customization
identifies background noise, music, silence, and other acoustic events
bias transcription toward domain-specific terms or key phrases
save transcripts as .txt files with optional timestamps at word or character level
processes mp3, wav, mp4, m4a, ogg, flac, webm and other common audio/video formats
specify 1-32 speakers for optimized diarization accuracy
choose between none, word-level, or character-level timestamps for precise timing data
Example Output
Example 1: Basic podcast transcription
[Speaker 1 - 0:00-0:15]: "Welcome to the tech podcast. Today we're discussing AI deployment strategies."
[Speaker 2 - 0:16-0:42]: "Thanks for having me. The key challenge is managing model latency in production environments."
[Audio Event: Background Music] - 0:43-0:50
[Speaker 1 - 0:51-1:05]: "Can you walk us through your approach?"
Example 2: Meeting transcription with key terms
[Speaker 1 - CEO] - 0:00-0:30: "Q3 results show strong adoption of our API infrastructure."
[Speaker 2 - CFO] - 0:31-1:15: "Revenue grew 45% YoY. The machine learning pipeline optimization reduced costs significantly."
[Audio Event: Side Conversation] - 1:16-1:25
[Speaker 3 - Engineer] - 1:26-2:10: "Our deployment strategy now includes automated canary releases and real-time monitoring."
What's Included
- elevenlabs-transcribe SKILL.md: Complete skill definition with argument parsing and API integration
- ElevenLabs Scribe v2 API wrapper: Handles authentication, file streaming, and response formatting
- Parameter templates: Pre-built examples for language codes, speaker count configurations, and custom keyterm lists
- Output formatting guide: Markdown templates for speaker-labeled transcripts with timestamps
- Error handling checklist: Common issues (missing API key, unsupported formats, rate limits) and solutions
Who It's For
- Podcast producers & audio engineers — Generate searchable transcripts with speaker labels for distribution and SEO
- Researchers & academics — Transcribe interviews, lectures, and focus group discussions with speaker identification
- Meeting facilitators & note-takers — Convert team meetings, client calls, and webinars into timestamped transcripts
- Content creators & journalists — Rapidly transcribe raw audio from field recordings, interviews, and multimedia projects
- Software engineers & DevOps teams — Integrate transcription into CI/CD workflows for accessibility and documentation
Best For
- Multilingual audio transcription across 32+ languages with language-specific optimization
- Identifying and separating multiple speakers in interviews, panels, meetings, and podcasts
- Detecting non-speech audio events (music, noise, silence) for post-production analysis
- Domain-specific transcription (medical, legal, technical) using custom keyterm biasing
- Batch processing audio/video files from multiple sources with consistent formatting and timestamps
You might also like
When a user uploads a file to Claude, you can intelligently detect its type and read it using the appropriate method. Instead of blindly running cat on binary files or loading massive CSVs into context, this skill routes each file type to the right tool, reading only what's needed to answer the user's question. You'll extract text from PDFs, parse structured data from CSVs and JSON, process images, and decompress archives—all without wasting context or producing garbage output.
by seifbenayed
This skill detects your project structure, installs Portless globally, and configures your dev scripts to use stable named URLs instead of port numbers. It handles monorepo detection, suggests appropriate subdomain naming conventions, and updates your package.json automatically—saving you from manual configuration and port conflict headaches.
by qdhenry
You can perform end-to-end PDF operations including extracting text and metadata from documents, merging multiple PDFs into a single file, splitting PDFs by page ranges, filling fillable forms programmatically, and adding text overlays to non-fillable PDFs. This skill handles both simple read operations and complex document workflows, making it essential for document processing, form automation, and PDF batch operations.
by seifbenayed
You can input historical ticket volume data, agent availability, skill distributions, and cost constraints into Claude to systematically identify coverage gaps and generate optimized shift schedules. The skill surfaces non-obvious solutions like identifying when part-time coverage outperforms full-time hiring, pinpointing cross-training opportunities to improve flexibility, and calculating labor cost trade-offs for different scheduling scenarios—enabling you to make evidence-based decisions that balance operational efficiency with SLA compliance.
by qdhenry
You can deploy Cloudflare Workers scripts, configure KV Storage and R2 buckets, manage DNS records, set up Pages deployments, and handle routing rules—all directly from Claude. The skill automatically validates your API credentials, extracts live deployment URLs, and surfaces clear error messages when configuration issues arise.
by qdhenry
Set up continuous monitoring of specific directories or file types, then automatically trigger Claude prompts whenever files change. Perfect for real-time code validation, design-to-code synchronization, test generation, or configuration updates. Each changed file is processed through your custom prompt with full access to its contents.
by qdhenry
You can design complete REST API specifications from requirements, translating them into resource-oriented endpoint architectures that follow industry best practices. Claude generates OpenAPI 3.0 schemas with validated request/response definitions, ensures correct HTTP method semantics and status code usage, and produces Swagger documentation ready for Swagger UI, ReDoc, or Postman integration. Catch design anti-patterns and naming inconsistencies before implementation.
Query your local Screenpipe instance to retrieve screen recordings, audio transcriptions, UI element accessibility trees, keyboard/mouse input logs, and productivity analytics. You can search by keywords, filter by content type (audio, OCR, accessibility, input), set time ranges, and extract structured data about your applications, meetings, and work sessions without sending data to external servers.
by az9713