This submission is for the AssemblyAI Challenge: No More Monkey Business.
What I Built
Assembla is your go-to AI-powered app that turns conversations into actionable insights—fast. It handles multi-channel audio like a pro, syncs voice and text seamlessly, and generates summaries that actually make sense. Built with AssemblyAI’s APIs, this app keeps things simple, smart, and scalable.
I’m part of the Aloware Technical Team, where we use cutting-edge tech to make communication smarter and smoother. AssemblyAI is one of our MVPs, helping us level up user experience with transcription and summarization tools that streamline conversations.
At Aloware—a call center as a service (CCaaS) platform—we already rock AssemblyAI for our Smart Transcription feature. With Assembla, I wanted to push the boundaries by building features on the client side, showing how you can whip up production-ready tools that are efficient, sleek, and quick to develop.
Demo
✨ Live App: Assembla Live
✨ GitHub Repo: Source Code
Screenshots
Journey
This project is powered by AssemblyAI’s LeMUR API, flexing its muscles to deliver real-time transcription and meaningful summaries.
At Aloware, we’ve been crushing it with AssemblyAI, using it to boost our Smart Transcription services. This project took inspiration from those tools and spun them into a client-side prototype, proving you can build robust AI-powered features without getting buried in backend complexity.
Key Highlights:
- Multi-channel audio support for seamless conversations.
- Real-time transcription and summarization using AssemblyAI’s API.
- Synced playback to keep audio and text perfectly aligned.
- Custom prompts to generate summaries that actually work for you.
AssemblyAI APIs Used
-
Upload API (
https://api.assemblyai.com/v2/upload)- Description: This API uploads audio files to AssemblyAI’s server and returns a unique URL to reference the audio. It’s the first step to enable transcription.
- Use Case in Assembla: Used to seamlessly upload user audio files and prepare them for processing.
-
Transcription API (
https://api.assemblyai.com/v2/transcript)- Description: This API initiates the transcription process and returns a unique transcription ID. It starts the process of converting audio into text.
- Use Case in Assembla: Creates a transcription request for uploaded audio and initiates the processing.
-
Transcription Status API (
https://api.assemblyai.com/v2/transcript/${transcriptionId})- Description: This API fetches the current status of the transcription request and retrieves the final transcription result when ready.
- Use Case in Assembla: Tracks progress and fetches the complete transcription once processing is complete.
-
LeMUR Summarization API (
https://api.assemblyai.com/lemur/v3/generate/summary)- Description: This API generates custom summaries of the transcribed content based on specific prompts.
- Use Case in Assembla: Used to create tailored summaries like action items, key takeaways, or next steps to help users maximize the value of their conversations.
Features
- Multi-Channel Audio Support: Handles conversations with multiple speakers without breaking a sweat.
- AI-Powered Transcription and Summarization: AssemblyAI’s tech brings crisp transcriptions and custom summaries to life.
- Synced Voice and Text Playback: Play audio while following along with perfectly synced text.
- Customizable Prompts: Get summaries tailored to your needs—action items, outcomes, unresolved issues—you name it.
- Client-Side Build: No backend drama, just fast, scalable, and lightweight features.
Why It Stands Out
- AI-Powered Everything: Smarter, faster, and more accurate.
- Action-Ready Summaries: Stop wading through data; get what you need instantly.
Zero Clutter: Clean design, smooth functionality, no distractions.
Tech Stack: Vue.js, TailwindCSS, and AssemblyAI’s magic.
Thanks for checking out Assembla! Ready to transform your conversations into actionable insights?
✨ Live App: assembly-ai.netlify.app
✨ GitHub Repo: Source Code
Top comments (0)