Average Ratings 0 Ratings
Average Ratings 0 Ratings
Description
Ink 2 represents Cartesia's most advanced and precise streaming speech-to-text model, designed specifically for production voice agents, boasting the lowest word error rate and superior turn detection of any available streaming STT. This model excels in accurately transcribing structured data types like phone numbers, dates, and email addresses on the first attempt, while intuitively recognizing when a speaker begins and ends their speech, eliminating the need for a separate voice activity detection mechanism. Integrated turn detection allows voice agents to respond to events seamlessly, rather than sifting through raw transcript segments. Ink 2 generates a comprehensive array of turn events, providing agents with definitive cues regarding when to listen, interrupt, contemplate, prepare to respond, retract an untimely reply, or engage in conversation. Additionally, the transcript retains a cumulative nature within each turn, ensuring that every update presents the complete text transcribed up to that point rather than just the incremental changes, and the emitted text is considered final the moment it is sent. This innovative design enhances the interaction quality between voice agents and users, making conversations smoother and more effective.
Description
TML-Interaction-Small is a multimodal interaction model created by Thinking Machines Lab that enables continuous real-time collaboration between humans and AI across audio, video, and text modalities. The model is designed to move beyond traditional turn-based AI systems by supporting native interaction capabilities such as simultaneous listening and speaking, proactive interjections, visual cue awareness, real-time responses, and ongoing contextual collaboration. TML-Interaction-Small processes interactions through a time-aligned micro-turn architecture that continuously exchanges 200ms streams of input and output, allowing the model to maintain conversational presence while reasoning, responding, and acting concurrently. The system combines an interaction model with an asynchronous background model that handles deeper reasoning, tool usage, browsing, and long-running workflows while the primary interaction layer continues communicating with the user in real time. The architecture allows users to collaborate with AI more naturally through speech, video, messaging, and multimodal inputs without waiting for rigid conversational turn boundaries. Thinking Machines Lab developed the model to improve human-AI collaboration by keeping people actively involved during AI workflows rather than relying solely on autonomous agents. TML-Interaction-Small includes capabilities such as live translation, contextual interruptions, visual-based reactions, concurrent speech processing, time awareness, tool calling, web browsing, and multimodal streaming interaction. The system also introduces encoder-free early fusion techniques, streaming inference optimization, and reinforcement learning strategies optimized for interactive responsiveness and stability.
API Access
Has API
API Access
Has API
Integrations
No details available.
Integrations
No details available.
Pricing Details
No price information available.
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
Cartesia
Founded
2023
Country
United States
Website
docs.cartesia.ai/build-with-cartesia/stt/latest
Vendor Details
Company Name
Thinking Machines Lab
Country
United States
Website
thinkingmachines.ai/