Stream

Today, we’re releasing the first version of our Vision AI framework! It's 100% open-source and has over 10 out-of-the-box plugins for @krispHQ, @ultralytics, @cartesia, @OpenAI, @GoogleAIStudio, and more! With Vision Agents, developers can build fast, low-latency vision AI applications running on Stream from day one with just a few lines of Python ⚒️

[say playfully] New TTS model release 🚨 Inworld’s TTS-2 model brings natural language steering, pause controls, rich emotions, prompting and much more. Upgrade to the latest version of Vision Agents to get started and check out @inwrold_ai release for more details 🧵👇

@visionagents_ai @xai @neevash Brutal 😂

Built a conference companion with the new @xai Grok Voice Think Fast 1.0 model. It can look up people you're meeting at a conference, scrape their X posts, make and persist notes about them, and roast whoever you like! Sorry @neevash 🤷‍♂️ All entirely in real-time!

This was one of the most rewarding demos I've created. It really feels like we're at the point where avatars can actually provide real value and genuinely improve how we interact with technology!

The stream integration is live: a few lines of code in stream's @visionagents_ai framework adds a real-time face to any agent An interactive avatar turns an agent into a natural interface, leading to better outcomes: higher conversion, lower cost to serve, increased usage, faster adoption Read more anam.ai/blog/vision-ag… Sign up at lab.anam.ai

Full walkthrough here: builder.aws.com/content/3ClgBp…

Live video is the easy part. The chat layer is where teams quietly rebuild things twice. New tutorial w/ @AWS: ship a production-grade live streaming app with Amazon IVS + Stream Chat. • IVS Low-Latency + Real-Time WebRTC, sub-300ms • Stream Chat: <40ms, 5M concurrent, 99.999% SLA • SOC 2, ISO 27001, HIPAA, GDPR Read the full tutorial on AWS Builder Center 👇

Developers have been building with Stream for over a decade. Now their AI agents can too. 🎉 Find us on skills.sh/getstream

🚨 New Vision Agents release v0.5.5 bring support for the latest @xai models as well as @inworld_ai Realtime API and more. Check out our full release notes on Github⚒️ github.com/GetStream/Visi…

To pineapple or to not pineapple? @max_does_tech built a voice agent using @inworld_ai's Realtime API to answer the age old question 🍕 Quickstart: visionagents.ai/introduction/v… Example code: github.com/GetStream/Visi…

Anam avatars are live in Vision Agents 🔥 Two lines of Python and your agent has a face. What @Anam__ai brings: • Custom avatars from a photo or a prompt • Every frame rendered live from the agent's voice • Ultra-low latency for natural pauses and turn-taking • Realism benchmarked independently • 50+ languages with native lip sync We're exploring the use cases a voice agent alone can't pull off: An AI fitness coach that watches how you move and perform. An interviewer that picks up on tone and posture. A language coach that can read facial expressions, and so much more. The cookbook is live! Start building today and feel free to share your projects in our discord! discord.com/invite/RkhX9Px…

Thank you @getstream_io for this great case study with @tsur_roee about @popup_fm getstream.io/blog/popup/

Anam is now integrated with @visionagents_ai @getstream_io's open-source multimodal agent framework handles orchestration, state management, and the realtime pipeline. Drop Anam in as the face layer and the agent joins the call with a live generated face that reacts to what it sees and hears. What you can build: - a tutor reading student body language + eye contact - a sales coach catching the micro-signals a rep misses - an onboarding agent that sees confusion before it escalates Docs: anam.ai/cookbook/visio…

We’re excited to collaborate with @TencentRTC to support their WebRTC transport in Vision Agents! If you’re building agents in China and across Asia, join our early access program to try the Tencent RTC transport: visionagents.ai/integrations/e…

Learn more 👇. getstream.io/blog/best-on-d…

Discover, compare, and use VibeVoice, Qwen3-TTS, Neu TTS, TADA TTS, Pocket TTS, and Kitten TTS for voice generation in your next app.

New text-to-speech (TTS) models are released each week, but it is difficult to know which ones can run privately and locally on edge devices. We have tested and shortlisted the Top 6 On-Device TTS Models for Any AI Project below.

What's new: - Anam avatar integration: your agent gets a synced face with interruption handling - LocalEdge: prototype with your mic, speakers, and camera. No Stream account needed - Helm charts for Kubernetes deployment - Deepgram TTS moved to persistent WebSocket - major latency drop - Fixed resource leaks in long-running deployments 100% open source: getstream.io/blog/vision-ag…

Building multimodal AI agents that actually run in production is a different game from demo-ware. Memory leaks, connection cleanup, deployment infra, latency - the boring stuff matters most. Vision Agents v0.5.0 is focused on exactly that 👇 x.com/visionagents_a…