January 2025
Model
NGen-Realtime-Omni Multimodal
NGen-Realtime-Omni Multimodal is a true omni-modal assistant that processes text, audio, and image inputs in real-time for instantaneous interactions. Engineered for low-latency responses with 125K token context length, making it ideal for real-time communication and multimodal applications.
Overview
NGen-Realtime-Omni Multimodal is a true omni-modal assistant that processes text, audio, and image inputs in real-time for instantaneous interactions. Engineered for low-latency responses with 125K token context length, making it ideal for real-time communication and multimodal applications.
Key Capabilities
- Real-time processing of text, audio, and image inputs
- Low-latency responses for instantaneous interactions
- 125K token context length with 32K max generation
- Transformer-based multimodal architecture
Applications
Ideal for live transcription and analysis, interactive voice agents, real-time video analysis, and multimodal communication systems requiring instantaneous processing across multiple input types.
Pricing
Rs 1.25 input / Rs 1.66 output per 1K tokens
Availability
Served from every TNSA region.
India South
in-south
India Central
in-central
US East-1
us-east-1
Build with TNSA models
Explore model families, snapshots, and developer tools for production AI systems.