Newspatrolling.com News cum Content Syndication Portal Online
Model achieves industry-leading accuracy for code-mixed speech, eliminating translation layers and enabling voice AI for India’s multilingual population
Gurugram, India : January 19, 2026: Shunya Labs, a research-driven voice AI company, today announced the launch of Zero Codeswitch, a speech recognition foundation model designed to understand naturally code-mixed and multilingual Indian speech.
Building on Shunya Labs’ achievement of 3.10% Word Error Rate (WER) on the OpenASR leaderboard:a 48% improvement over the next-best competitor:Zero Codeswitch is engineered to run efficiently on standard CPUs, reducing deployment costs by up to 20x while maintaining sub-100ms latency for real-time applications.
Most existing voice systems are optimized for single-language speech. In India, however, everyday conversations frequently blend Hindi, English, and regional languages within the same sentence, using transliteration, colloquial expressions, and informal grammar. This has historically posed a major challenge for voice AI systems, particularly outside major urban centers.
Zero Codeswitch is designed to process such mixed-language speech natively, without relying on intermediate translation layers that convert Indian languages into English. Instead, it uses a unified architecture capable of generating mixed Hindi and English tokens, allowing it to accurately transcribe natural phrases such as “Mujhe account balance dekhna hai.”
Unlike global models that are primarily trained on English data and later adapted for Indian languages, Shunya Labs’ foundation models are trained from the ground up on Indian speech data. Zero Codeswitch has been trained on millions of hours of real-world Indian audio, capturing variations in accent, dialect, pronunciation, slang, and transliteration. The model is optimized for Hinglish and code-mixed speech while being part of a broader Shunya Labs platform that supports more than 200 languages, including over 40 Indian languages.
The company expects Zero Codeswitch to serve as core infrastructure for voice-based applications across sectors such as fintech, healthcare, and government services:particularly in regions where English proficiency is limited and voice remains the most practical digital interface.
Ritu Mehrotra, CEO and Co-Founder of Shunya Labs, said: “Shunya Labs was built with a focus on deep research rather than short-term marketing narratives. With Zero Codeswitch, we are building foundational technology for Indian languages that prioritizes accuracy, latency, and real-world usability. Our goal is not just to adopt AI, but to build it at the foundation level in India.”
Sourav Bandyopadhyay, CTO and Co-Founder of Shunya Labs, said: “‘Shunya’ represents our philosophy of starting from first principles. With Zero Codeswitch, we are creating an intelligence layer that truly listens:engineered for India’s linguistic diversity and optimized for real-world deployment.”
Zero Codeswitch is designed for enterprise and public-sector use cases where data privacy is critical. The model can be deployed on-premises or in air-gapped environments, allowing organizations to train domain-specific variants while retaining full control over their data. Shunya Labs maintains compliance with HIPAA, SOC 2 Type II, and ISO 27001 standards, and supports CPU-first deployments that reduce dependency on specialized GPU infrastructure.
Headquartered in Gurugram, Shunya Labs is part of a growing ecosystem of companies building domestic intellectual property in core AI technologies. The company’s models are benchmarked against global competitors and are already being adopted by customers in India and abroad.
Availability Zero Codeswitch is available now for enterprise pilots and production deployment. Organizations can request access at www.shunyalabs.ai/zero-code-switch.
