i keep seeing all of these amazing hype reels that people are saying opus 5.5 created with a single prompt.
one shot, yeah right.. liars!! so i tried it.
prompt: "make a dynamic 15-second motion graphics video that shows what an incredible motion designer you are, like it's your showreel for a resume. go all out"
Is your voice agent moody? It should be!
With Gemini 3.8 Flash-Lite TTS, you can direct its mood or let the agent decide for itself. Cheerful, furious, wistful, apologetic, it nails all of them and sounds great.
Give it a try on LiveKit: livek.it/obFIyE5
Is your voice agent moody? It should be!
With Gemini 3.8 Flash-Lite TTS, you can direct its mood or let the agent decide for itself. Cheerful, furious, wistful, apologetic, it nails all of them and sounds great.
Give it a try on LiveKit: livek.it/obFIyE5
The coolest part of Gemini 3.5 Transcribe Live is the Smart Transcription mode!
It removes filler words and false starts, resolves self-corrections, and formats speech for readability as it happens.
Check it out: docs.livekit.io/agents/model…
The coolest part of Gemini 3.5 Transcribe Live is the Smart Transcription mode!
It removes filler words and false starts, resolves self-corrections, and formats speech for readability as it happens.
Gemini 3.5 Transcribe Live is now available in LiveKit Agents, bringing LLM-based realtime transcription built for alphanumerics, domain-specific vocabulary, multilingual speech, and code-switching.
Give it a try today on LiveKit Inference: docs.livekit.io/agents/model…
Protect sensitive data without giving up voice agent observability.
LiveKit PII Redaction automatically removes personal information from transcripts and recordings before it is stored. It is included with LiveKit Agent Observability at no additional cost.
Read more: bit.ly/4gJ1ex7
re:Invent early bird ends Aug 25. $1,299 instead of $2,499.
I've gone before and I'm going again, Nov 30 to Dec 4 in Vegas. Most of the week you spend with your hands on a keyboard.
bit.ly/3RDBOr5
Sponsored by @awscloud
But is Gemma 4 smart? It is.
88% task completion on our hotel receptionist eval, 75.6% on IFBench against GPT-5.5's 75.9%, and 76.9% on tau-2.
Price is $0.40 per 1M input tokens ($0.20 cached) and $1.20 per 1M output tokens.
To use Gemma 4 on LiveKit Inference, just change out one line in your LiveKit Agent:
llm="google/gemma-4-31b-it"
This give you access to the fastest voice AI llm with a single API key.
At LiveKit we benchmarked time to first token across the LLMs people actually put in voice agents. Gemma 4 31B on LiveKit Inference came back at 192ms. GPT-4.1 came back at 1,006ms.
Here's where that speed comes from, and how to switch.
Still super impressed by the newspapers from @aiDotEngineer world’s fair. Best thing I’ve seen at an event in a long time. Great work @MLHacks and @ThePracticalDev.
Beginning July 20, Claude Fable 5 will be included in all Max and Team Premium plans, at 50% of limits.
Pro and Team Standard users will continue to have access to Fable via usage credits, and will receive a one-time $100 credit.
Demand for Fable has been challenging to predict, which is why we rolled it out to subscription plans in stages, extending access several times as we secured additional capacity.
Happy to announce that I'll be speaking (again) at THE Commit Your Code Conference in Dallas - Sept 3-4.
For those that don't know, this conference is amazing! 100% of the proceeds go to charity. If you've never been to a developer conference before this is a great one to start with.
Tickets: commityourcode.com#CYC26
Look ma, I made it!!
So humbled to be among these amazing speakers.
I’ll be giving a 3 hour workshop on building open source voice AI agents for production at @AllThingsOpen.
I built a way to call my Solo workspace from a phone.
Ask "any of my agents waiting on me?" The voice agent fans out and reports who is stuck. Tell it the answer. It queues your message into the right terminal. The agent unblocks.
LiveKit Agents wrapping Solo's MCP.
Voice cloning is now available on LiveKit Inference. We’re launching with @inworld and @cartesia.
Clone a voice once and use it across multiple TTS providers, with automatic fallback to the same voice if a provider fails mid-call.
Free to create and available on all paid plans today.
I've been trying out Solo by @aarondfrancis and I'm loving it!
Found a little bug: it seems that rich live transient-mode TUIs scroll instead of redrawing.
For only 3 hours, come check out our VIP concierge demos today at the AI Garden booth, Startup Hub. Badge scan in, custom agenda out, keepsake video to remember it. Gemini and LiveKit end to end.
Headed to Vegas. #GoogleCloudNext starts tomorrow at Mandalay Bay. If you're building voice or multimodal agents, come find me at the Startup Hub. Let's talk Gemini and LiveKit.