Hey 👋, this weekly update contains the latest info on our new product features, tutorials, and our community.
New Features for Real-Time Transcription: Custom Silence Threshold and Utterance Control
You can now customize the silence threshold for automatic utterance detection and programmatically force the end of an utterance, giving you precise control over when your real-time stream produces a final transcript. These enhancements are especially valuable for latency-sensitive applications, such as voice bots, allowing you to fine-tune your real-time transcription experience for optimal performance.
Both utterance controls can be applied with a simple request. For more information and code examples, visit our docs.
Fresh From Our Blog
AI trends in 2024: Graph Neural Networks: From fundamental research to productionized AI models, discover how this cutting-edge technology is powering production applications and may be shaping the future of AI. Read more>>
What AI Music Generators Can Do (And How They Do It): Text-to-music models are advancing rapidly with the recent release of new platforms for AI-generated music. This guide focuses on MusicLM, MusicGen, and Stable Audio, exploring the technical breakthroughs and challenges in creating music with AI. Read more>>
Transcribe Phone Calls in Real-Time using Node.js with AssemblyAI, and Twilio: evelop an application that transcribes a Twilio phone call to text in real-time. Read more on Twilio's blog.
Our Trending YouTube Tutorials
Easy Text-to-Video in Python | Python Tutorial with Damo-vilab Model: This Python tutorial will show you how to use the the state-of-the-art Damo-vilab text-to-video model to create videos from text input.
How to Index Podcasts with Keywords like on Huberman's Website: Learn to build an application that indexes podcast episodes based on keywords using Speech-to-Text.
The Physics of Generative AI - How AI models use physics to generate novel data: Modern Generative AI is capable of generating entire stories and photorealistic images, but how do these models actually work?
