Build a Bengali voice agent on Bolna

​

Choose a Bengali transcriber

​

Choose a Bengali voice

​

Write the prompt for Bengali

• Write in Bengali script, not romanized Bengali. নমস্কার! আপনি কেমন আছেন? rather than Nomoskar! Apni kemon achhen?. 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 Bengali script text instead of forcing a pure Bengali translation.
• Set gender and politeness explicitly. These are often carried by verb forms, so name the forms you want for the agent’s persona rather than writing “be polite”.
• 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 Bengali agent over the API

{
  "agent_config": {
    "agent_name": "Bengali Support Agent",
    "agent_welcome_message": "নমস্কার! আমি আপনাকে কীভাবে সাহায্য করতে পারি?",
    "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": "bn",
          "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": "bn",
            "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": "আপনি একজন সহায়ক সাপোর্ট এজেন্ট। সংক্ষেপে উত্তর দিন।"
    }
  }
}

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.
• Gemini is not in the provider support table for these fields.

​

Fix pronunciation of numbers and names

​

Serve Bengali and English on one agent

• Code-mixing within a sentence. Sarvam and Soniox transcribe callers who mix English into Bengali; on Soniox, pick the multilingual option. A sentence with a few English words is still treated as Bengali.
• A full language switch. Add both English and Bengali to one agent with multilingual_config, each with its own transcriber, voice and prompt. Bengali 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 Bengali. The multilingual quickstart shows the API shape.

• Start a call in Bengali with "agent_data": { "language": "bn" } on POST /call, or an agent_language column set to bn 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 Bengali 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