Average Ratings 0 Ratings
Average Ratings 0 Ratings
Description
OpenAI has introduced GPT-Realtime-2, a voice model designed for dynamic live interactions that allows for seamless conversation flow while it processes requests, utilizes tools, addresses corrections, or manages interruptions, all while providing timely and relevant responses. This model is specifically crafted for a new generation of voice applications that aim to deliver a more intuitive user experience, respond with greater intelligence, and perform actions instantly. By incorporating GPT-5-level reasoning capabilities into voice interactions, GPT-Realtime-2 enhances agents' abilities to comprehend user intent, maintain context, adapt to changing requests, and utilize tools without disrupting the conversation. Developers have the option to implement brief preambles, such as “let me check that,” to inform users that the agent is currently processing their inquiry, and the model is capable of simultaneously engaging multiple tools while making its actions clear through phrases like “checking your calendar” or “looking that up now.” Additionally, it boasts improved recovery mechanisms, extended context for agent-driven tasks, and enhanced retention of specific terminology, contributing to a more effective communication experience. Overall, GPT-Realtime-2 is set to redefine how voice interactions are experienced, paving the way for smoother and more efficient user-agent dialogues.
Description
Mercury 2 represents a groundbreaking advancement in reasoning models, specifically designed for real-time voice interaction as it can quickly answer phone calls. Unlike traditional autoregressive models that leave callers in silence while generating responses one token at a time, Mercury 2 employs a diffusion large language model architecture capable of producing over 1000 tokens per second with standard NVIDIA GPUs. This remarkable speed allows it to complete a full reasoning process and begin speaking within a timeframe that aligns with natural conversational flow, effectively shortening the typical wait time from several seconds to approximately 300 milliseconds. The operational mechanism of Mercury models involves transforming clear text into noise, after which a conventional Transformer is trained to reverse this transformation and predict the original text across all positions at once. By utilizing a denoising approach that engages multiple tokens simultaneously, generation becomes more efficient, enabling speeds akin to custom silicon on NVIDIA H100s while improving responsiveness in voice applications. As a result, Mercury 2 not only enhances user experience but also sets a new standard for interactive voice technologies.
API Access
Has API
API Access
Has API
Integrations
OpenAI
Cerebras
GPT-4.1
Groq
Inception Labs
LiveKit
Pipecat
Retell AI
Vapi AI
gpt-realtime
Integrations
OpenAI
Cerebras
GPT-4.1
Groq
Inception Labs
LiveKit
Pipecat
Retell AI
Vapi AI
gpt-realtime
Pricing Details
$32 per 1M tokens
$32 / 1M audio input tokens ($0.40 for cached input tokens) and $64 / 1M audio output tokens
Free Trial
Free Version
Pricing Details
No price information available.
Free Trial
Free Version
Deployment
Web-Based
On-Premises
iPhone App
iPad App
Android App
Windows
Mac
Linux
Chromebook
Deployment
Web-Based
On-Premises
iPhone App
iPad App
Android App
Windows
Mac
Linux
Chromebook
Customer Support
Business Hours
Live Rep (24/7)
Online Support
Customer Support
Business Hours
Live Rep (24/7)
Online Support
Types of Training
Training Docs
Webinars
Live Training (Online)
In Person
Types of Training
Training Docs
Webinars
Live Training (Online)
In Person
Vendor Details
Company Name
OpenAI
Founded
2015
Country
United States
Website
openai.com/index/advancing-voice-intelligence-with-new-models-in-the-api/
Vendor Details
Company Name
Inception
Country
United States
Website
www.inceptionlabs.ai/blog/mercury-2-the-first-reasoning-model-fast-enough-to-pick-up-the-phone