Mentor | Coach | Coder | AI Engineer
Austin, TX
Joined December 2010
- Tweets690
- Following543
- Followers2.3K
- Likes917
Give your LangChain tools a voice without wiring up STT, turn detection and TTS yourself.
Dialog-RSN-1 hears the caller and writes the reply; the API voices it. LangChain tools and a create_agent do the work. ~270 lines of Python, with tests.
petermckee.dev/blog/build-a-…
An agent behind a tool took 4 to 5 seconds in my runs. That's dead air on a call.
Mark one tool argument "poly_spoken": true and the model writes a line the server speaks while the tool runs. First words in about half a second.
The tests run the real agent against a fake realtime server. A fake that speaks the holding line in the same order as the real server caught a hang when the agent failed before the line finished.
Code: github.com/pmckeetx/dialog-r…
Peter McKee retweeted
“Hello? Is anyone there?” 🤔
That’s what callers say when a voice agent takes a beat too long. AI can write production code, but many agents still can’t tell when to speak on a live call.
Dialog-RSN-1 hears the caller’s audio and handles the whole turn in a single pass, so callers hear a reply in under 1 second. Independent benchmarking by Coval found it the strongest realtime model they’ve tested on production-style calls.
@pmckee, @Addlesee_AI, and @matthen2 take you inside the model in Part 1 of Let’s Dialog: Building the Next Voice Agents.
Grab your spot: bit.ly/4dVUc6B
A browser voice assistant in ~550 lines of JS. Mic audio streams to Dialog-RSN-1, which hears it directly, detects end of turn and streams the reply back as speech. No STT, LLM, TTS chain.
Ships as one <voice-assistant> custom element. Write-up:
petermckee.dev/blog/add-a-vo…
Audio: an AudioWorklet turns float32 into 16-bit PCM in 20 ms chunks at the native rate, and the server resamples. Replies are 24 kHz PCM16, scheduled as back-to-back AudioBuffers.
On barge-in the server cancels the reply. The client just flushes its queue.
Vite 8 library mode bundles React 19, the CSS and the worklet (as a Blob URL) into one ES module, ~81 kB gzipped, in a Shadow DOM.
Code, plus a test site to drop it into:
github.com/pmckeetx/dialog-r…
AI can write code, but on a live call it struggles to know when to speak.
Wed 4 Nov I'm hosting Matt Henderson and Angus Addlesee, who built Dialog-RSN-1, on turn-taking, barge-in and noisy lines.
12 pm ET: poly.ai/webinars/lets-dialog…
AI After Hours is for engineers, architects and product leads in London, in any industry.
You build a working agent at PolyAI HQ with our engineers at your table. Wed 14 Oct, 6 to 9 PM.
poly.ai/events/ai-after-hour…
AI After Hours, London, Wed 14 Oct, 6 to 9 PM.
Bring a laptop. Join a small team with a PolyAI engineer at the table and build a working agent for a bank or insurer in 90 minutes. AWS covers food and drinks.
poly.ai/events/ai-after-hour…
We've been running Dialog-RSN-1 in production for weeks
~250k live production ~2.5M model turns ~100k calls in the last 7 days ~50k on the peak day ~20 customer accounts
Speech-native. no transcript step, sub-300ms median model first-token.
poly.ai/blog/PolyAI-dialog-r…
A caller says "Matthew with two Ts." The ASR types "Matthew with to tease." Your LLM is done.
Dialog-RSN-1 skips the text bottleneck. Raw audio + conversation history + your prompt, so it hears what transcripts get wrong. Mood, noise, accents too.
poly.ai/dialog-rsn-1-early-a…
Most voice AI ends your turn with a silence timer. Pause to think and it talks over you. Dialog-RSN-1 moves that call into the model. Early Access: poly.ai/dialog-rsn-1-early-a…
Most voice AI throws away tone and emotion. Speech-to-speech locks your agent's voice.
Dialog-RSN-1 reasons over raw audio while letting you use your own TTS. Full audio reasoning, sub-300ms latency, zero voice lock-in.
Get early access: lnkd.in/gVJJkDkc
Headless browser scripts are the "it works on my machine" of automation. They’re brittle, resource-heavy, and high-maintenance.
Tabstack is a web execution layer. One API call handles browser interactions and data extraction. No Puppeteer bloat.
Try it: tabstack.ai
🥳 Tabstack is officially live and we're looking for feedback from the community.
If you're building agents or automation workflows, grab an API key and tell us what's missing. We're prioritizing the roadmap based on dev requests.
Get you API key here: tabstack.ai
Only 3 days left to register!
Build something cool with our Speech AI models and win $1,000!
We launched a challenge on @ThePracticalDev and we’re giving away 3x $1K for the best apps.
Join here and submit your project by November 24:
dev.to/challenges/assemblyai
📢 NYC devs! Join us for the AssemblyAI Hackathon on Fri, Dec 6! 🚀 A day packed with AI innovation, coding, and connections—plus food, caffeine, swag, and a happy hour to end the day! 🍻 Don’t miss out!🙌lu.ma/newafxrf #NYCHackathon #AI #DevCommunity
6 months ago we launched Universal-1. Today, Universal-2 pushes speech AI even further. See what's new: xitter.cf/AssemblyAI/status/1851…