The Agentic Post
Breaking
Perplexity vs ChatGPT Search vs Google AI Mode: Which AI Search Is Best in 2026?  ·  What Are Vision-Language-Action (VLA) Models? How Robots Learn to Follow Instructions  ·  How to Translate Documents With AI Accurately (and When Not To)  ·  MCP vs A2A: The Two AI Agent Protocols Explained in Plain English  ·  Is Grok Accurate for News? What Studies Show About AI Search Citations  ·  Is AI a Bubble? 7 Warning Signs Investors Are Watching in 2026  ·  
Home/AI Agents/Enterprise Agents
ElevenLabs Realtime v1: One Voice Model That Replaces the Whole Voice-Agent Stack

ElevenLabs Realtime v1: One Voice Model That Replaces the Whole Voice-Agent Stack

Enterprise Agents

ElevenLabs Eleven Realtime v1 Mini and Max turn a five-part voice agent stack into one model, with 0.57-second replies, 90+ languages and OpenAI Realtime API compatibility.

ElevenLabs has launched Eleven Realtime v1, a voice model that listens to speech and talks back directly, replacing the five or so separate pieces developers used to wire together to build a voice agent. It comes in two sizes, Mini and Max, starts speaking in about 0.6 seconds, works in more than 90 languages and is compatible with OpenAI’s Realtime API, so switching can take just a couple of code changes.

What problem does Eleven Realtime solve?

Building a phone or web voice agent used to mean stacking several systems: one to turn speech into text, one to detect when you stop talking, one to manage turn-taking, a language model to decide what to say, and a text-to-speech voice to say it. Each handoff adds delay and another thing to tune. ElevenLabs put the whole stack behind one model ID. As the company put it, you “shouldn’t have to become a configuration expert to build a voice agent that sounds natural,” per StartupHub.ai.

What is the difference between Mini and Max?

  • v1 Max: for complex jobs like customer support and lead qualification. About 0.57 seconds to first audio, 98.8% on the Big Bench Audio reasoning test and 87.1% success on tool-using tasks
  • v1 Mini: for natural everyday conversation. About 0.62 seconds to first audio, slightly better at handling pauses and turn-taking, but much weaker at reasoning (75.9%) and tools (60.3%)

ElevenLabs says these scores were evaluated by Artificial Analysis. They are company-reported figures, not our own tests.

Does it keep a text record of conversations?

Yes, and that matters for businesses. Instead of a single sealed audio-to-audio system, Eleven Realtime keeps text at every step inside its pipeline. That lets teams see exactly what the agent heard and what it decided to say, and lets ElevenLabs apply guardrails and hide personal data, which is harder with fully fused voice models.

Why does OpenAI compatibility matter?

Many voice apps are built on OpenAI’s Realtime API, such as those covered in our look at OpenAI’s GPT Live 1 for developers. Because ElevenLabs matches its message format, developers can change the endpoint and model name and keep the rest of their code. That makes it easy to test both and pick on price, voice quality or speed.

How much does it cost?

ElevenLabs charges per minute of connected audio plus language model tokens; exact rates are on its pricing page. It works inside ElevenAgents, with phone, web and WhatsApp channels, or directly through the Realtime API over WebSocket. Apps using WebRTC have to switch to WebSocket first.

Who should use it?

Teams building customer support lines, booking agents or sales assistants that need to sound natural and use tools. Any of ElevenLabs’ 17,000+ library voices can be used. Just remember the voice-cloning ground rules in our voice cloning explainer.

Up Next
OpenAI Images 2.6: GIFs, 50% Faster Images and New Flare and Sunburst Models

OpenAI Images 2.6: GIFs, 50% Faster Images and New Flare and Sunburst Models

ChatGPT

OpenAI Images 2.6 adds GIF creation, 50% faster generation and two API models, Flare and Sunburst. What changed and how to try it in ChatGPT.

OpenAI released Images 2.6 on November 4, 2026. It makes pictures about 50% faster than Images 2.5, can now create animated GIFs, and gives finer control over edits. It is available on every ChatGPT plan and in Codex, and developers get two API models: GPT-Image-2.6 Flare for speed and GPT-Image-2.6 Sunburst for detail.

What is new in Images 2.6?

  • GIFs: you can create short animated GIFs, including from a simple sketch
  • Speed: images arrive about 50% faster than with 2.5
  • A complexity setting: a new control that trades speed for quality when editing
  • Markup in the API: the ChatGPT feature that lets you circle exactly what to change now works for developers too

These details come from GIGAZINE’s summary of OpenAI’s announcement.

What is the difference between Flare and Sunburst?

Flare is the quick one: it can produce a low-quality image in about six seconds, which suits drafts, chat apps and thumbnails. Sunburst is the careful one: higher quality and more consistent when you edit the same image again and again, which suits product shots and brand work. Pricing is per token and unchanged from Images 2.5.

Is Images 2.6 the best AI image generator now?

On blind human votes, yes. On the Artificial Analysis leaderboard, Sunburst and Flare took the top two spots, ahead of the older 2.5 versions. It is also among the most expensive at maximum settings. Our November 2026 image generator comparison shows where cheaper rivals like Google’s Nano Banana 2.1 make more sense.

How popular is ChatGPT image generation?

Very. OpenAI said people create over 4 billion images a week, more than 500 million a day, across ChatGPT, Codex and the API.

How do I try it?

Open ChatGPT on web, desktop or mobile and ask for an image or a GIF. The update is rolling out to all plans, so it may take a few days to reach every account. For tips, see how to get better results from AI image generators.