New: Post-call analytics, Deepgram Flux improvements & more
Hey folks 👋 We've been shipping a steady stream of improvements to Layercode, based on your feedback. Here's what's new: Deepgram Flux improvements Fixed the 60-second silence disconnect bug that was interrupting some longer pauses. Deepgram Flux now works on Twilio calls when using your own Deepgram key (note: Cloudflare currently supports linear16 encoding only.) Post-call analytics Capture...
Faster, more expressive voice AI agents with Cartesia Sonic-3
Cartesia's Sonic-3 is now available on Layercode. Released last week, Sonic-3 is the fastest and most expressive production-ready TTS model: Incredible low-latency: 90ms model latency, 190ms end-to-end makes Sonic-3 ideal for real-time voice AI agents and one of the fastest TTS models available. Natural emotion and expressiveness: Sonic-3 handles laughter, excitement, and empathy. You can use...
Deepgram Flux: now available on the edge
We're excited to announce a major upgrade to Layercode: support for Deepgram Flux: the world's first transcription system built specifically for voice agents. What is Deepgram Flux? Traditional speech-to-text models are built for pure transcription, but voice agents need to understand the flow of conversation, not just capture words. To solve this, Deepgram built the world’s first...
Layercode CLI is now available
Building voice AI agents is tricky. There’s lots to remember: even when developing locally with a tool like Layercode, you need to remember to run a tunnel and add the correct URL to your dashboard so Layercode can send webhooks. This was annoying us, so we built Layercode CLI — a command-line interface designed to help you get started in minutes. What you get with Layercode CLI: Zero to...
Layercode FAQ
Dropping a bunch of frequently asked questions and answers here: How does Layercode work? Layercode uses a chained ‘voice pipeline’ approach to give LLM-powered AI agents the ability to listen to a user’s speech, transcribe and process the input, and respond with speech. Here’s how Layercode works: 1. Capture: A user’s speech is captured, and audio streams to nearest edge location. 2....
Layercode Startup Program - Get $2,000 in free credits to build voice AI startups
We believe every developer with a vision deserves the tools to build it. We're launching a Startup Program to give early-stage companies building innovative voice AI experiences access to world-class voice infrastructure. We're offering voice AI startups: $2,000 free: Start building immediately with $2,000 in platform credits. That's enough for thousands of minutes of conversation. Credits roll...
Feedback wanted: CLI to build your first voice AI agent in ~2 mins
Hey folks! We just released a CLI to help quickly build, test, and deploy voice AI agents straight from your dev environment. npx u/layercode/cli init https://www.youtube.com/watch?v=bMFNQ5RC954 Link to our full docs → We’d love feedback from devs building agents — especially if you’re experimenting with voice. What feels smooth? What doesn't? What’s missing for your projects?
New: Layercode CLI, bring your own keys, product and pricing updates
We just shipped several big and small updates: Get started faster from the CLI ⚡ We’ve made it much easier to create a voice AI agent straight from the command line. Just run: npx @layercode/cli init To scaffold a new project and get a local voice agent running in a few minutes. Here's a short video showing it in action → Bring your own keys for ElevenLabs & Cartesia 🔑 We want to make it as...
5 lessons from talking to 100+ teams building voice AI agents
Real-time voice AI is young, and the tools and infrastructure that will power its future are being built right now. After working with and speaking to hundreds of teams building voice AI agents, we’ve learned a lot. Some of the most important things: Voice AI demos are easy. Scaling to production is hard. Low latency is only one piece of the puzzle. Delivering consistent, reliable performance...
Text-to-Speech Voice AI Model Guide 2025
Anyone building voice AI agents knows how hard it is to stay up-to-date with the latest text-to-speech voice models. We spend time testing and experimenting with all of the available paid and open-source text-to-speech voice AI models and consolidated our own notes and experience testing different models into a single guide for developers evaluating multiple models. Read on for a quick primer...
How to write prompts for voice AI agents
We created a tactical guide sharing a bunch of best practice for developers on how to tune your prompts to make your voice agent's speech more conversational. Sharing the fundamentals here 👇 Written and spoken language are fundamentally different in a number of ways that impact how you should approach building voice AI agents. Consider how a human might communicate the same information:...