--- title: "Building performant voice agents in India" date: "2026-02-14" authors: "Varun Khurana" tags: "guide" --- # Building performant voice agents in India India is one of the world's fastest growing regions for voice agents. With LiveKit Cloud's regional agent deployment in Mumbai, you can deploy your voice agents in India to minimize latency. ## Key takeaway: co-locate your AI models near your voice agent The key to building fast voice agents on LiveKit is to host your agents in a region close to your entire AI model stack, including your STT (speech-to-text model), LLM (large language model), and TTS (text-to-speech model). There's two factors that affect the speed of your voice agent: *User ↔ Agent latency* and *Agent ↔ Model latency*. User ↔ Agent latency: - The audio packet between the user and the agent can run relatively uninterrupted over long distances on LiveKit's optimized private network. - This means it's okay to have users far away from where your agent is as long as your agent is close to your model stack. Agent ↔ Model latency: - Every call from the agent to the AI models is sequential (e.g. agent to LLM only runs after agent to STT finishes). - This includes any intermediary function calls your LLM might be making, such as to your database. - Because this path involves more steps and each call is dependent on the previous one, it's important that each individual agent-to-model call is done over the shortest possible path. The best way to do this is geographically co-locating each AI model with your agent. ### Voice agent latency comparison by architecture Let's use a example where a user and agent are both located in India, but the AI models are all located in the United States. Since the agents and models are not co-located, most requests are traveling between cloud regions, adding latency with each hop. ![Voice agent latency when models are not co-located](https://hvmycqjumkkwae8e.public.blob.vercel-storage.com/1image.png) When models and the agent are co-located, most requests are short with the long user to agent transport running on LiveKit's private network. ![Voice agent latency when models are co-located](https://hvmycqjumkkwae8e.public.blob.vercel-storage.com/2image.png) ## Building an India-based voice AI stack ### Model selection for Indian languages Because of the large number of regional dialects across India, it's important to choose STT and TTS models that have broad language support. Here's what's currently available through [LiveKit Inference](https://docs.livekit.io/agents/models/#inference) and [LiveKit Agents plugins](https://docs.livekit.io/agents/models/#plugins): | AI Model Type | Model Providers | **Indian Language Support** | | ------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------ | | **STT** | [Deepgram Nova-3](https://docs.livekit.io/agents/models/stt/deepgram/) (via LiveKit Inference, hosted in India) | Hindi and 7 other languages. Auto-routes to India regional deployment. | | **STT** | [Cartesia Ink Whisper](https://docs.livekit.io/agents/models/stt/cartesia/) (via LiveKit Inference) | 100+ languages, including Hindi | | **STT** | [Sarvam AI](https://docs.livekit.io/agents/models/stt/sarvam/) (via LiveKit Agents plugin) | Hindi, Tamil, Telugu, Kannada, Malayalam, Bengali, Marathi, Gujarati, Punjabi and more | | **TTS** | [Cartesia](https://docs.livekit.io/agents/models/tts/cartesia/) (via LiveKit Inference) | Multilingual, including Hindi | | **TTS** | [ElevenLabs](https://docs.livekit.io/agents/models/tts/elevenlabs/) (via LiveKit Agents plugin) | 29+ languages, including Hindi | | **TTS** | [Rime](https://docs.livekit.io/agents/models/tts/rime/) (via LiveKit Inference) | Multilingual, including Hindi | | **TTS** | [Sarvam AI](https://docs.livekit.io/agents/models/tts/sarvam/) (via LiveKit Agents plugin) | 11 Indian languages, including Hindi, Tamil, Telugu, Bengali, Marathi, Gujarati, Kannada, Malayalam, Punjabi, Odia | | **LLM** | [Azure OpenAI](https://docs.livekit.io/agents/models/llm/azure-openai/) (India) / [Vertex Gemini](https://docs.livekit.io/agents/models/llm/gemini/) (asia-south1) (via LiveKit plugins) | 50+ languages, including Hindi and other Indic languages | | **LLM** | [Sarvam AI](https://docs.livekit.io/agents/models/llm/sarvam/) (via LiveKit Agents plugin) | Tuned for Indian languages, with tool calling support | If you want to minimize latency to serve users within India, here's an example stack we would recommend: | **Layer** | **Provider** | **Notes** | | ----------------- | --------------------------------------------------- | -------------------------------------------------------------------------------------- | | **Agent hosting** | LiveKit Cloud Mumbai (ap-south) | Deploy agents in LiveKit India's ap-south region. | | **STT** | Deepgram (via LiveKit Inference) | Requests go to Deepgram's API through LiveKit Inference. | | **LLM** | Azure OpenAI (India) or Vertex Gemini (asia-south1) | Use Azure's or Google's India cloud regions. | | **TTS** | Cartesia (via LiveKit Inference) | Routed to Cartesia's India region through LiveKit. Failovers in-region not guaranteed. | ### When and how to host voice agents in India With LiveKit Cloud's agent deployment region in Mumbai (ap-south), you can host your agent in India. To optimize for the lowest latency experience, the best option is to host your agent and call AI models within the same region. However, if you need specific models only available in other regions (e.g., latest GPT, specialized TTS voices), it's best to host your agent in the region nearest your models rather than your end users. ### Telephony for voice agents in India For voice agents handling calls in India, we recommend using a regional SIP trunk provider. Using a SIP trunk has a few advantages: - **Local phone numbers**: Indian users are far more likely to pick up a call from a local number (+91) than an international one. Local numbers also enable features like DND registry compliance. - **Better call quality**: Calls that originate and terminate within India avoid international hops, reducing jitter and packet loss. - **TRAI Regulation**: Indian telecom regulations (TRAI) have specific requirements around number provisioning, call handling, and caller ID that using a SIP trunk helps with. All telephony calls are subject to further Department of Telecommunications (DoT) data residency requirements. LiveKit works with most SIP trunk providers. Here's how to get started: - Get phone numbers from a local SIP provider ([Plivo](https://docs.livekit.io/telephony/start/providers/plivo/), [Twilio](https://docs.livekit.io/telephony/start/providers/twilio/), Exotel). - Configure your SIP trunk [to point to LiveKit's India SIP endpoint](https://docs.livekit.io/telephony/features/region-pinning/#region-based-endpoint). - Deploy your agent in LiveKit Cloud's Mumbai (ap-south) region. ### Additional considerations for LiveKit voice agents in India - **Questions**: If you have any questions about optimal setup or compliance requirements, reach out [here](https://livekit.com/contact-sales) or in our [community](https://community.livekit.io/). Regulatory and data residency requirements vary by customer and use case. - **Getting Started**: Check out the [LiveKit Agents quickstart](https://docs.livekit.io/agents/start/voice-ai/) to get your first agent running, then adapt with the India stack config above.