Customer support · Production

Meesho delivers real-time multilingual customer support at scale with ElevenLabs voice agents

The problem

Meesho needed to deliver empathetic, human-like customer support at scale across multiple languages and use cases for its large and diverse user base.

Workflow diagram · grounded in source
1
Customer initiates support call
Trigger
Customers call Meesho support in Hindi or English to ask about orders and deliveries.
▾ source quote
“This bot now handles high-volume queries about order and delivery statuses like delays, cancellations, etc. – all in natural, spoken conversation”
2
Voice agent processes query
Ai action
A real-time voice agent built with ElevenLabs Text to Speech handles customer queries in natural, spoken conversation.
▾ source quote
“They built a real-time voice agent using ElevenLabs Text to Speech to automate customer support in both Hindi and English. This bot now handles high-volume queries about order and delivery statuses like delays, cancellations, etc. – all in natural, spoken …”
3
Autonomous resolution without handoff
Output
The bot resolves queries about order delays, cancellations, and refunds without human intervention.
▾ source quote
“It resolves a high volume of queries without human intervention – covering order delays, cancellations, and refunds – while reducing average handling time”
Reported outcome

The voice bot handles over 60,000 customer calls daily in Hindi and English, resolves a high volume of queries without human intervention covering order delays, cancellations, and refunds, and reduces average handling time.

Reported metrics
Customer calls handled dailyover 60,000
Average handling timereducing average handling time
User engagementhigher user engagement
User feedbackoverwhelmingly positive feedback
Show all 5 reported metrics
customer calls handled dailyover 60,000
average handling timereducing average handling time
user engagementhigher user engagement
user feedbackoverwhelmingly positive feedback
resolution accuracyhigh accuracy
Reported stack
ElevenLabs Text to SpeechElevenLabs Conversational AI
◆ Does this fit your context?

Compare to your context

Tell us your scale, team, and constraints. We'll show what changes at your size, what fails at your scale, and whether this case is a fit, needs adaptation, or won't scale to you. Free demo, no signup.

Compare to your context →
~30 seconds · free
Source
https://elevenlabs.io/blog/meesho
Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

The voice bot handles over 60,000 customer calls daily in Hindi and English, resolves a high volume of queries without human intervention covering order delays, cancellations, and refunds, and reduces average handling…

What tools did this team use?

ElevenLabs Text to Speech, ElevenLabs Conversational AI.

What results were reported?

Customer calls handled daily: over 60,000; Average handling time: reducing average handling time; User engagement: higher user engagement; User feedback: overwhelmingly positive feedback (source-reported, not independently verified).

How is this customer support AI workflow structured?

Customer initiates support call → Voice agent processes query → Autonomous resolution without handoff.

Related customer support cases

WHAT TO DO WITH THIS

Now compare it to your context

This case is one data point. Whether its pattern fits you depends on your volumes, your stack, and your exception load — that comparison is the step no case study can do for you.

Browse the Customer support cases →