Assemblyai · Blogs

Blogs listings from Assemblyai on TechiSeek. 372 public listings.

• Review - SimCLS and RefSum - Summarization Techniques (Assemblyai)
  This week’s Deep Learning research papers are SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarization and RefSum:…
• Redact PII in Audio with Make and AssemblyAI (Assemblyai)
  Create a Make scenario using the AssemblyAI app that watches a Google Drive folder for new audio files, and then creates both a transcript…
• Review - Pretraining Representations for Data-Efficient Reinforcement Learning (Assemblyai)
  In recent years, pretraining has proved to be an essential ingredient for success in the fields of NLP and computer vision.
• Review - VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning (Assemblyai)
  This week's Deep Learning Paper Review is VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning.
• Recurrent Neural Networks (RNNs) Explained (Assemblyai)
  In this video, we learn what Recurrent Neural Networks (RNNs) are and how they work.
• Real-time speech-to-text: the complete developer guide (Assemblyai)
  Real-time speech-to-text converts speech into text within milliseconds as audio streams—the layer that makes live captions, meeting tools,…
• When to stop self-hosting Whisper (and what you actually gain) (Assemblyai)
  Self hosting Whisper gets expensive fast. See the real GPU, DevOps, and scaling costs, plus when a managed speech-to-text API makes more se…
• LLM Gateway: The easiest and most reliable way to call multiple LLMs (Assemblyai)
  All through a single OpenAI-compatible endpoint, with zero markup on provider costs. It's the easiest and most reliable way to call multipl…
• Raw WebSocket Voice Agent with AssemblyAI (Assemblyai)
  The bare protocol — every event named, every state transition logged, no SDK in between you and the wire.
• Redact Personally Identifiable Information (PII) from audio with Node.js (Assemblyai)
  In this tutorial, you will learn how to automatically redact Personal Identifiable Information from audio and video files with Node.js and…
• Review - ALBERT: A Lite BERT for Self-supervised Learning of Language Representations (Assemblyai)
  This week’s Deep Learning Paper Review is ALBERT: A Lite BERT for Self-supervised Learning of Language Representations.
• Quick Automatic Chapter Detection (Assemblyai)
  In this tutorial, you will learn how to do automatic chapter detection using the AssemblyAI API in an easy-to-follow tutorial.
• Speech-to-Text Accuracy on Podcasts, News Broadcasts, and Social Media (Assemblyai)
  In this report, we look at 12 different audio/video files from various sources, and review how accurately AssemblyAI, AWS Transcribe, and G…
• Review - A Graph Convolutional Neural Network for Emotion Recognition in Conversation (Assemblyai)
  In this week's Deep Learning Paper Review, we look at the following paper: DialogueGCN: A Graph Convolutional Neural Network for Emotion Re…
• What is Regularization? Overfitting and Neural Networks (Assemblyai)
  In this video, we will learn about Regularization, a common technique that is used to deal with overfitting in ASR.
• Real-time STT latency benchmarks: what "fast enough" means for voice agents (Assemblyai)
  Every voice agent evaluation eventually lands on the same fight: latency. Someone pulls up a benchmark, sees one provider faster than anoth…
• PyTorch vs TensorFlow in 2023 (Assemblyai)
  Should you use PyTorch vs TensorFlow in 2023? This guide walks through the major pros and cons of PyTorch vs TensorFlow, and how you can pi…
• Real-time speech recognition with Python (Assemblyai)
  Add real-time speech recognition to a Python app: stream microphone audio with PyAudio, handle turn events from the SDK, and tune turn dete…
• Real-Time Transcription in Python with Universal-3.6 Pro Realtime: Build in 5 Minutes (Assemblyai)
  Build real-time transcription in Python with streaming WebSockets and Universal-3.6 Pro Realtime.
• How Grain increased customer satisfaction by 12% after integrating AssemblyAI (Assemblyai)
  AI notetaker Grain partners with AssemblyAI to power its conversation intelligence offering, boosting its customers’ productivity and satis…
• Real-time transcription that code-switches for multilingual speakers (Assemblyai)
  Learn how Universal-Streaming enables real-time transcription for multilingual speakers who naturally code-switch mid-sentence, handling si…
• Reinforcement Learning With (Deep) Q-Learning Explained (Assemblyai)
  In this video, we learn about Reinforcement Learning and (Deep) Q-Learning.
• How to remove or reduce background noise from audio for (stt) transcription (Assemblyai)
  Remove background noise from audio with simple online tools or software for clear recordings, podcasts, and videos.
• Analyzing and scoring voice agent calls with the LLM Gateway (Assemblyai)
  Now comes the harder question, the one that decides whether it stays in production: how do you know if it's any good?
• Review - data2vec: A General Framework for Self-supervised Learning in Speech, Vision, and Language (Assemblyai)
  This week's Deep Learning Paper Review is data2 vec: A General Framework for Self-supervised Learning in Speech, Vision, and Language.
• Review - JUST: Joint Unsupervised and Supervised Training For Multilingual ASR (Assemblyai)
  This week's Deep Learning Paper Review is JUST - JOINT UNSUPERVISED AND SUPERVISED TRAINING FOR MULTILINGUAL ASR.
• Real-time Speech Recognition with AssemblyAI (Assemblyai)
  Building responsive voice applications has never been more accessible. With AssemblyAI's Universal-Streaming model, you can create real-tim…
• Real-time entity extraction from speech: Capturing emails, phone numbers, and addresses in live (Assemblyai)
  Real time entity extraction from audio captures emails, phone numbers, and addresses during live calls.
• How to perform speaker diarization in JavaScript (Assemblyai)
  Speaker diarization answers "who spoke when?" in multi-speaker recordings by partitioning audio into segments based on speaker identity.
• Prompting Claude to build voice agents (Assemblyai)
  Claude can write voice agent code in seconds. Shipping it is about context, not wording.
• RLHF vs RLAIF for language model alignment (Assemblyai)
  RLHF is the key method used to train AI assistants like ChatGPT, but it has strong limitations and can produce harmful outputs.
• Releasing our v8 Transcription Model - 18.72% Better Accuracy (Assemblyai)
  Today, we’re happy to release our most accurate Speech Recognition model to date - version 8 (v8).
• Review - Text-Free Prosody-Aware Generative Spoken Language Modeling (Assemblyai)
  In this week's Deep Learning Paper Review, we look at the following paper: Text-Free Prosody-Aware Generative Spoken Language Modeling.
• Pipecat voice agent with AssemblyAI Universal-3.6 Pro Realtime (Assemblyai)
  Build a real-time voice agent using Pipecat — the open-source Voice AI framework — and AssemblyAI's Universal-3.6 Pro Realtime model as the…
• Review - Decision Transformer & SPIRAL (Assemblyai)
  This week’s Deep Learning Paper Reviews are Decision Transformer: Reinforcement Learning via Sequence Modeling and SPIRAL: Self-supervised…
• How CBB Labs enabled a dance studio to run 4× faster with AssemblyAI (Assemblyai)
  CBB Labs built Sangs, a voice agent powered by AssemblyAI, for DanceHall Studios, a studio-management platform for South Asian classical da…
• Real-time vs batch transcription: What (Assemblyai)
  When you’re building Voice AI applications, one of the first decisions you’ll make is how audio gets transcribed: in real time as it stream…
• Announcing Our $28M Series A Led by Accel | AssemblyAI (Assemblyai)
  We’re excited to share that we’ve raised a $28M Series A led by Accel, with participation from a great group of investors including Y Combi…
• Prompt engineering for real-time speech-to-text (Assemblyai)
  The market believes you can't prompt a streaming speech-to-text model. Our benchmarks prove you can — and that it's the single biggest accu…
• Python speech recognition in 30 lines of code (Assemblyai)
  In this simple tutorial, we learn how to implement Speech Recognition in Python with just 30 lines of code.
• Introducing the Postman collection for AssemblyAI (Assemblyai)
  Postman is a user-friendly tool for API testing, enabling users to send requests, debug, and automate tests within a collaborative environm…
• What is real-time speech to text? (Assemblyai)
  Real-time speech to text converts spoken words into accurate text instantly for live captions, meeting transcription, and voice commands as…
• Should I build or buy an AI speech recognition system? (Assemblyai)
  Deciding between building an in-house ASR model and buying an API? Compare accuracy, internal resources, speed of iteration, and data secur…
• How Dovetail improved WER by 36% with AssemblyAI to power continuous customer intelligence (Assemblyai)
  Learn how a leading customer intelligence platform integrated Assembly to boost WER by 36% and improve customer experience.
• Why real-time is the future of speech-to-text (Assemblyai)
  The highest-value speech-to-text work now happens while people are still talking — voice agents, agent assist, live captions, ambient scrib…
• 29 questions to ask when building AI voice agents (Assemblyai)
  AI voice agents look amazing in demos, but in production…sometimes, not so much. Over 60% of AI agent implementations fail to meet performa…
• Review - Perceiver: General Perception with Iterative Attention (Assemblyai)
  This week’s Deep Learning Paper Review is Perceiver: General Perception with Iterative Attention.
• Raw WebSocket voice agent with AssemblyAI (Python) (Assemblyai)
  This is the simplest voice agent: a microphone, a raw WebSocket, and Universal-3.6 Pro Realtime streaming speech-to-text—no SDK, no framewo…
• Podcasts About AI - Our Deep Learning Team’s Top Picks (Assemblyai)
  For each podcast discussed, you’ll find a description, the average episode length, frequency, and some of our favorite episodes.
• How to build a voice agent with Python in 5 minutes (Assemblyai)
  Build a voice agent in Python that listens, thinks, and talks back — AssemblyAI for real-time speech-to-text, OpenAI for responses, and Ele…