Can I identify different speakers in a single recording?

Yes, the skill includes configuration options for speaker diarization, allowing you to distinguish between multiple participants in a conversation.

What is the Nova-2 model used in this workflow?

Nova-2 is Deepgram's state-of-the-art speech-to-text model, designed for industry-leading accuracy and speed across diverse audio types.

What audio formats are supported by this Deepgram skill?

The skill supports common audio formats including WAV, MP3, FLAC, OGG, M4A, and WebM, with automatic MIME-type detection.

Does this skill support real-time audio streaming?

This specific skill (Workflow A) is optimized for pre-recorded audio; for real-time streaming, you should use the Deepgram Core Workflow B skill.

How are large audio files handled?

The workflow includes error handling for timeouts and suggests using batch processing or callback URL patterns for processing exceptionally large files.

Deepgram Pre-recorded Audio Transcription

Name: Deepgram Pre-recorded Audio Transcription
Author: Brmbobo

byBrmbobo

0•

Desarrollo de API

Implements high-accuracy speech-to-text transcription workflows using the Deepgram Nova-2 model for pre-recorded audio files and URLs.

This skill provides a standardized framework for integrating Deepgram's transcription capabilities into your projects. It enables developers to quickly set up service classes in TypeScript or Python to handle audio transcription from both local files and remote URLs. With built-in support for advanced features like speaker diarization, smart formatting, and punctuation, this skill is perfect for building robust batch processing pipelines, podcast transcription services, or automated meeting summary tools using the high-performance Nova-2 model.

Características Principales

010 GitHub stars

02Comprehensive error handling for timeouts and unsupported formats

03Dual-mode transcription for local files and remote URLs

04Advanced speaker diarization and smart formatting options

05Pre-built TypeScript and Python service implementation patterns

06Support for Deepgram Nova-2 high-performance transcription model

Casos de Uso

01Processing bulk meeting recordings for searchable text archives

02Integrating speech-to-text features into enterprise SaaS applications

03Automating podcast transcriptions with multi-speaker identification

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add brmbobo/web2podcast deepgram-core-workflow-a

For use in Claude.ai and ChatGPT

Características Principales

010 GitHub stars

02Comprehensive error handling for timeouts and unsupported formats

03Dual-mode transcription for local files and remote URLs

04Advanced speaker diarization and smart formatting options

05Pre-built TypeScript and Python service implementation patterns

06Support for Deepgram Nova-2 high-performance transcription model

Casos de Uso

01Processing bulk meeting recordings for searchable text archives

02Integrating speech-to-text features into enterprise SaaS applications

03Automating podcast transcriptions with multi-speaker identification

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add brmbobo/web2podcast deepgram-core-workflow-a

For use in Claude.ai and ChatGPT