api

research

community

careers

community

careers

api

research

natural-sounding ai loan inquiry agent

answer loan enquiries with clear explanations of loan options and application requirements

see what it's like to talk to a voice agent

…

these are demo agents. they can't take real actions or give real support, so please don't share personal details.

clone this agent ↗

leave the everyday calls to your loan inquiry agent

build on what the borrower already knows to make the next step easier to understand

loan enquiries
the loan inquiry agent asks what the borrower needs funding for and explains the relevant loan information supplied by the lender
application requirements
walks through the documents needed for the loan being discussed using the lender's instructions to clarify anything the borrower is unsure about
questions for follow-up
collects the specific questions a borrower wants to discuss with a loan officer along with their contact details for a follow-up conversation

set up your loan inquiry agent in three steps

start with a template or build from scratch around the conversations the agent needs to handle

choose from 8 agent templates
pick a template for the work you want the agent to handle, or build your own from scratch.
configure the prompt and voice
set the agent’s role in its system prompt and choose from 4 voices for its calls.
deploy for web or phone
connect your live agent to your website or phone number so customers can speak with it.

build agents that know what to ask and when to act

routine requests keep moving with the agent, while the team focuses on the calls that need them.

4 voices, up to 11 languages

choose the voice your customers hear from your agent and let them talk in a language they use every day.

voices

siya · ira · aisha · zoya

languages

customer context from the first hello

bring customer details from your systems into the call, so the agent gets to the real question without asking for the basics again.

ananya

home loan

enquiry on 2 october

voice agent

“hi ananya, thanks for your home loan enquiry. what can i help with?”

custom tools for the next step

build custom tools that connect to your systems, so the agent looks up records, creates tickets, or updates information during a call.

loan info

crm

callbacks

loan details found

enquiry saved

callback requested

one agent for web and phone calls

the agent you build for your site can answer a phone line, and your api can place a phone call with that same agent.

web call

loan questions?talk to our voice agentstart call

incoming calloutgoing call

voice agent00:24

a conversation history for every loan inquiry agent

look back at what the caller asked and how the agent responded before deciding what comes next

voice agents

prompt

conversations

loan inquiry agent

system instruction

you are a responsible loan inquiry voice agent for a bank or lender. help callers understand loan categories, eligibility factors and how to request a callback. ask one question at a time and collect only high-level details such as loan purpose, approximate amount and preferred contact time.

first greeting

hi, i can help with your loan inquiry. what type of loan are you interested in?

deploytest live

voice

silk mulberry 1.6

languages

english

speaker

siya

conversations

calldate & time

web call29 sep, 11:12 am

web call29 sep, 2:38 pm

web call28 sep, 4:05 pm

web call27 sep, 10:20 am

web call26 sep, 6:47 pm

web call

completed

0:00 / 0:48

voice agenthi, i can help with your loan inquiry. what type of loan are you interested in?
a home loan. i'm looking at a flat in pune.
got it. roughly how much are you looking to borrow?
around 40 lakh. i work at a software company.
thanks. when would be a good time for a callback?
tomorrow evening, after six, works for me.

view call summary

call summary

the caller asked about a home loan for a flat in pune and shared an approximate amount of 40 lakh, mentioning that they work at a software company. the agent asked for a preferred callback time, and the caller asked for a call tomorrow evening, after six.

clear pricing for every conversation

unlimited

plans start at ₹9,999/month

unlimited silk agent usage

choose 1, 2, 4, or 8 concurrent lines

capacity shared across your account

pay as you go

starts as low as ₹1.99/min

silk mulberry agent

₹1.99/min

silk muga agent

₹2.99/min

includes 4 shared concurrent slots

pay for what you need

clear pricing for every conversation

silk mulberry

unlimited

sota tts model

plans start at ₹9,999/month

per 1k characters

unlimited silk agent usage

₹0.50

choose 1, 2, 4, or 8 concurrent lines

capacity shared across your account

silk muga

pay as you go

sota voice design

starts as low as ₹1.99/min

per 1k characters

silk mulberry agent

₹0.99

₹1.99/min

silk muga agent

₹2.99/min

includes 4 shared concurrent slots

silk spider

our most advanced model

contact the team for preview access

frequently asked questions

you must add the lender's document requirements to its instructions or supply them through variables. specify which requirements belong to each loan type so the agent has the information needed to answer the applicant's question.

the rumik playground lets you create the loan inquiry agent from a matching template where available or build it from scratch. its instructions define how it handles calls, so setup starts with the business information it needs and how it should respond. once the voice, languages, and any required tools are configured, test a conversation before deploying it.

yes, the same deployed agent can handle both. incoming calls reach it through a connected rented number or sip trunk, while outbound calls are started through rumik's api.

this requires a custom tool connected to the lender's application system. the lender must implement the necessary access and applicant-verification checks in that connection before returning a status for the agent to explain.

with silk mulberry 1.6, the loan inquiry agent can speak 11 languages: english, hindi, bengali, gujarati, kannada, malayalam, marathi, punjabi, tamil, telugu, and urdu. its voice settings let you choose which of these languages it should use, along with one of four voices: ira, aisha, siya, or zoya.

its response can be defined in the playground's system instruction field. for example, the instructions can tell it to acknowledge that it cannot confirm an answer and ask for contact details for follow-up. if that request needs to become a support ticket, a custom tool connected to the support system can create it during the call.

on pay as you go, the loan inquiry agent can handle up to 4 simultaneous calls when all account slots are available. each call occupies 1 slot for its duration, and those slots are shared with other agents and text-to-speech requests. unlimited plans offer 1, 2, 4, or 8. capacity above 8 slots is available through sales.

pay-as-you-go pricing is ₹1.99 per minute for mulberry agent calls and ₹2.99 per minute for muga. for a fixed monthly bill, unlimited plans cover agent usage at the selected simultaneous capacity, starting at ₹9,999/month for 1 slot. either option has separate phone-number rental and carrier charges.

build your first voice agent

join us

we are a close-knit group of researchers, engineers, and designers working on the hardest problems in ai.

2026 - rumik intelligence private limited

join us

we are a close-knit group of researchers, engineers, and designers working on the hardest problems in ai.

join us

natural-sounding ai loan inquiry agent

natural-sounding ai loan inquiry agent

see what it's like to talk to a voice agent

see what it's like to talk to a voice agent

see what it's like to talk to a voice agent

loan enquiries

application requirements

questions for follow-up

set up your loan inquiry agent in three steps

set up your loan inquiry agent in three steps

set up your loan inquiry agent in three steps

choose from 8 agent templates

configure the prompt and voice

deploy for web or phone

4 voices, up to 11 languages

customer context from the first hello

custom tools for the next step

one agent for web and phone calls

frequently asked questions

frequently asked questions

frequently asked questions

build your first voice agent

build your first voice agent

compare

compare

contact

contact

careers

careers

research

research

ira

ira

privacy policy

privacy policy

terms

terms

ai glossary

ai glossary

playground

playground

text to speech

text to speech

api keys

api keys

voice agents

voice agents

pricing

pricing

docs

docs

support

support

x

linkedin

discord

instagram

youtube

we are a close-knit group of researchers, engineers, and designers working on the hardest problems in ai.

text to speech

text to speech

playground

playground

ai glossary

ai glossary

api keys

api keys

voice agents

voice agents

pricing

pricing

documentation

documentation

support

support

compare

compare

contact

contact

careers