open source transcript seeker assemblyai

Transcription interface using the AssemblyAI API

Transcription Playground leveraging the AssemblyAI API, with an MIT License

Transcript Seeker integrates with AssemblyAI's transcription API, providing an open-source interface for AssemblyAI's speech-to-text capabilities.

With this integration, you can:

Upload audio or video files for transcription using AssemblyAI's API
View transcripts synchronized with your media
Navigate content by selecting specific words in the transcript
Use AssemblyAI's speaker diarization for multi-speaker content
Access additional API features such as summarization, named entity recognition, and sentiment analysis

As an open-source project, Transcript Seeker allows for customization and extension of AssemblyAI API integrations.

The AssemblyAI API integration in Transcript Seeker includes:

File upload to AssemblyAI's servers
Transcription initiation with configurable options
Result polling and retrieval
Processing and organizing speaker utterances
Handling of additional features like summarization and entity detection

AssemblyAI API options available in the implementation:

Speaker labels (diarization)
Summarization (with customizable model and type)
Entity detection
Sentiment analysis
Auto chapters

This implementation allows developers to modify or extend the AssemblyAI API integration as needed.

View on GitHub
 
import { z } from 'zod';

export const options = z.object({
  speaker_labels: z.boolean().describe('Speaker Diarization').optional(),
  summarization: z.object({
    summarization: z.boolean().describe('Enabled').optional(),
    summary_model: z.enum(['informative']).default('informative').describe('Summary Model'),
    summary_type: z.enum(['bullets']).default('bullets').describe('Summary Type'),
  }),
  entity_detection: z.boolean().describe('Named Entity Recognition').optional(),
  sentiment_analysis: z.boolean().describe('Sentiment Analysis').optional(),
  auto_chapters: z.boolean().describe('Chapterization').optional(),
});

transcript seeker interface assemblyai api

To use Transcript Seeker with the AssemblyAI API integration:

Save the script below as run.sh and make it executable:

chmod +x run.sh
./run.sh

Open the application in your browser once the development server starts.
Navigate to "Settings" and enter your AssemblyAI API key.
Choose "AssemblyAI" as the transcription service when uploading a file.

Ensure Git, Node.js, and Yarn are installed on your system before running the script.

View on GitHub
 
#!/bin/bash
# 🚀 Quick Start for Transcript Seeker 🚀
# Save this file as run.sh, chmod +x run.sh, and run it
# ⚠️ Make sure you have Git, Node.js, and Yarn installed before proceeding!

# clone and navigate to the repo
git clone https://github.com/Meeting-Baas/transcript-seeker && cd transcript-seeker

# Install dependencies
echo "🔧 Installing dependencies..."
yarn install && yarn install:all || { echo "❌ Error: Failed to install dependencies"; exit 1; }

echo "🏗️ Building dependencies..."
yarn run build || { echo "❌ Error: Failed to build dependencies"; exit 2; }

echo "📄 Copying .env file..."
cp .env.example .env || { echo "⚠️ Warning: Failed to copy .env file. You may need to set up environment variables manually."; }

echo "🚀 Starting the development server..."
cd client && yarn run dev || { echo "❌ Error: Failed to start the development server"; exit 3; }