Build a Telugu voice agent on Bolna

​

Choose a Telugu transcriber

​

Choose a Telugu voice

​

Write the prompt for Telugu

• Write in Telugu script, not romanized Telugu. నమస్కారం! మీరు ఎలా ఉన్నారు? rather than Namaskaram! Meeru ela unnaru?. Native script gives more accurate pronunciation and stops the text being treated as English.
• Keep common English loanwords in Latin script. Callers say “order”, “OTP” and “support ticket” in English, so keep those words as they are inside Telugu script text instead of forcing a pure Telugu translation.
• Set politeness explicitly. Ask for the polite plural (మీరు) rather than the informal singular. A generic “be polite” instruction does not reliably produce it.
• Read alphanumerics character by character, in English. For OTPs, registration numbers and order IDs, this avoids misheard and mispronounced digits.
• Leave language switching out of the prompt. Bolna switches languages itself.

​

Create a Telugu agent over the API

{
  "agent_config": {
    "agent_name": "Telugu Support Agent",
    "agent_welcome_message": "నమస్కారం! నేను మీకు ఎలా సహాయం చేయగలను?",
    "tasks": [{
      "task_type": "conversation",
      "toolchain": { "execution": "sequential", "pipelines": [["transcriber", "llm", "synthesizer"]] },
      "tools_config": {
        "llm_agent": {
          "agent_type": "simple_llm_agent",
          "agent_flow_type": "streaming",
          "llm_config": { "provider": "openai", "model": "gpt-4.1-mini", "max_tokens": 150, "temperature": 0.2 }
        },
        "transcriber": {
          "provider": "sarvam",
          "model": "saaras:v4",
          "language": "te",
          "stream": true,
          "endpointing": 500,
          "keywords": "Bolna, PhonePe, Flipkart",
          "context": "Inbound support line for an electronics retailer in India. Callers ask about order status and returns, and often read out order numbers."
        },
        "synthesizer": {
          "provider": "sarvam",
          "provider_config": {
            "voice": "Priya",
            "voice_id": "priya",
            "model": "bulbul:v3",
            "language": "te",
            "speed": 1.0
          },
          "stream": true,
          "buffer_size": 150
        },
        "input": { "provider": "plivo", "format": "wav" },
        "output": { "provider": "plivo", "format": "wav" }
      },
      "task_config": { "call_terminate": 90, "hangup_after_silence": 10 }
    }]
  },
  "agent_prompts": {
    "task_1": {
      "system_prompt": "మీరు ఒక సహాయక సపోర్ట్ ఏజెంట్. క్లుప్తంగా సమాధానం ఇవ్వండి."
    }
  }
}

curl https://api.bolna.ai/v2/agent \
  -H "Authorization: Bearer $BOLNA_API_KEY" \
  -H "Content-Type: application/json" \
  -d @agent.json

import os, urllib.request, json

with open("agent.json") as f:
    body = json.load(f)

req = urllib.request.Request(
    "https://api.bolna.ai/v2/agent",
    data=json.dumps(body).encode(),
    headers={"Authorization": f"Bearer {os.environ['BOLNA_API_KEY']}",
             "Content-Type": "application/json"},
)
print(json.load(urllib.request.urlopen(req)))

​

Improve recognition with keywords and context

• keywords: a comma-separated list of terms callers say.
• context: a sentence or two describing the call.

• Sarvam: keywords on Sarvam needs saaras:v4, and takes up to 50 terms of up to 64 characters each. context works on every Saaras model.
• Soniox: reads both. context can run to about 10,000 characters.
• Smallest AI: reads keywords, with an optional weight per term such as Bolna:5, up to 100 terms. It has no context field.
• Gemini is not in the provider support table for these fields.

​

Fix pronunciation of numbers and names

​

Serve Telugu and English on one agent

• Code-mixing within a sentence. Sarvam and Soniox transcribe callers who mix English into Telugu; on Soniox, pick the multilingual option. A sentence with a few English words is still treated as Telugu.
• A full language switch. Add both English and Telugu to one agent with multilingual_config, each with its own transcriber, voice and prompt. Telugu is one of the languages Bolna detects automatically, so with the default “requested or auto detected” trigger the agent follows a caller who moves into Telugu. The multilingual quickstart shows the API shape.

• Start a call in Telugu with "agent_data": { "language": "te" } on POST /call, or an agent_language column set to te in a batch CSV. Inbound calls can return agent_language from your caller data source.
• Let system messages such as the hangup and “are you still there?” checks follow the active language.
• Read How language switching works for what does and doesn’t trigger a switch.

​

Phone numbers for Telugu agents in India

• Buy an Indian number in the dashboard through Plivo or Vobiz.
• For commercial or telemarketing calls in India, read How to get 140 & 160-series phone numbers in India for the TRAI and DLT requirements.
• To use numbers from your own carrier, connect it with a SIP trunk.

​

Next steps