GTM Recruiter

SquadStack launches Arth V2 speech model for indian-language calls. SquadStack launched Arth V2, an in-house speech-to-text model for Indian customer calls. The company reported an 8.85% semantic word error rate and 67-millisecond latency on its own benchmark, while making the model available in closed beta. 12 Oct 2026 16:35 IST SquadStack.ai has launched Arth V2, a speech-to-text model designed for Indian-language customer calls, as the company seeks to reduce transcription errors in voice-based artificial intelligence (AI) systems used for sales and customer interactions. The company said Arth V2 recorded a semantic word error rate of 8.85% and a latency of 67 milliseconds on its internal Conversational Streaming Automatic Speech Recognition (ASR) Benchmark, which uses 863 real Indian sales calls recorded over 8 kHz telephone audio. According to SquadStack, the model produced fewer meaning-changing transcription errors than several competing systems, including models from Sarvam, Google, OpenAI and ElevenLabs. These results are based on the company's own benchmark and have not been independently verified. The Noida-based company said Arth V2 has processed more than one crore minutes of live customer calls over two months. The model is deployed within SquadStack's voice AI agents for enterprise customers and is also available in closed beta for organisations seeking to test it on their own call recordings. Benchmark focuses on indian-language conversations. SquadStack said its benchmark was designed to reflect conditions in Indian contact centres, where customers frequently switch between languages, speak over agents and make calls against background noise. More than 80% of the speech minutes in the test dataset are code-mixed, while nearly 90% contain background noise, according to the company. The recordings use narrowband telephone audio, which captures a more limited frequency range than the wideband recordings commonly used in speech-recognition testing. The benchmark measures semantic word error rate, which focuses on transcription mistakes that alter the intended meaning rather than treating every word substitution as equally consequential. SquadStack reported that Arth V2 recorded fewer meaning-changing errors than Sarvam Saaras v4, Google Gemini 3.5 Transcribe, OpenAI gpt-live-transcribe and ElevenLabs Scribe v2 Realtime. However, the release also acknowledged that Soniox v5 recorded a marginally lower error rate of 8.77%, compared with Arth V2's 8.85%. The company said Arth V2 delivered its final transcript within 67 milliseconds of a customer stopping speaking on 80% of turns. It reported that the model was faster than the competing systems in its tests, although the release did not provide a complete set of comparable latency measurements for every model. SquadStack said the benchmark's test audio, reference transcripts and scoring methodology are available on Hugging Face, allowing other developers to evaluate their own speech-recognition systems against the dataset. Company builds in-house Speech Recognition. Arth V2 is the latest version of SquadStack's in-house speech-recognition technology. The company said it trained the model from scratch using more than 60 crore minutes of Indian sales conversations, covering over 10 crore unique speakers. According to SquadStack, Arth currently handles 80% of the more than 50 lakh AI calls the company makes each day. Its chief technology officer, Vikas Gulati, said the company plans to release updated versions of the model every few weeks as it identifies and addresses transcription errors in production. The approach is intended to improve the speech-recognition component of voice AI agents, where an incorrectly transcribed amount, date or customer response can affect the system's subsequent action. Apurv Agrawal, co-founder and chief executive officer of SquadStack, said transcription remains a significant failure point for voice AI agents because downstream language models depend on correctly capturing what a customer says. The company provides voice AI agents for consumer sales and said it works with more than 60 large brands, including Kotak Mahindra Bank, PhonePe, Angel One and IndiaMART. The launch comes as companies deploy conversational AI systems for customer support, sales and other telephone-based interactions. For these applications, performance on real-world telephone audio may differ from results obtained using clean recordings or general-purpose speech benchmarks. Arth V2's broader performance will depend on how it compares with competing models across independently evaluated datasets, languages and use cases beyond SquadStack's own customer calls.

London-based AI voice startup ElevenLabs is betting big on India, hosting a summit in Bengaluru for close to 1,000 attendees. Chief executive officer Mati Staniszewski said that if the company can crack how people interact with AI in India, it can "solve it anywhere in the world." India is already its largest market outside the US. ElevenLabs plans to invest "hundreds of millions of dollars" there, and wants to expand support from 14 Indian languages to all 22 officially recognised ones. The company raised $500 million in February and completed a $300 million employee tender offer that doubled its valuation to $22 billion. It has signed up more than 250 enterprises and recently opened a Singapore office.

ElevenLabs, a US-based AI voice software company, has opened a Singapore office to serve as its Southeast Asia hub. The company's regional clients include Funding Societies, Atome, AI Rudder Rezonate, and Level3AI. The expansion follows ElevenLabs' July launch of data residency in Singapore, offering local hosting, zero-retention options, and lower latency across Singapore and East Asia. The company is also hiring locally, with an enterprise sales position advertised. ElevenLabs raised $500 million at an $11 billion valuation. The Singapore presence addresses regional businesses' multilingual operations and data location considerations for compliance with Singapore's Personal Data Protection Act.