Add real-time voice conversations to your React or Next.js app in minutes. Drop in the <EdesyWidget /> component from @edesy/voiceai-react, or wire up the useEdesy() hook to build a fully custom voice UI. Prefer no npm install? The same one-line script tag works too.
One Install
Or Script Tag
Custom UI
Latency
Pick the level of control you want
Render <EdesyWidget publicKey agentId /> anywhere in your tree. You get the floating button, voice panel, and WebRTC audio out of the box.
Wrap your app in <EdesyProvider> and call useEdesy() to build a completely custom voice UI—your buttons, your design, your states.
Developer path with @edesy/voiceai-react
Everything you need for a custom voice UI
Programmatically begin and end a voice session—trigger it from any button, event, or flow in your app.
Know when a call is live so you can render the right state, animations, or an active-call indicator.
Read mute state and toggle the microphone from your own custom controls.
Access the live transcript to render captions, chat-style history, or log the conversation.
Track call length in real time for timers, billing displays, or analytics.
Handle mic-permission and connection errors gracefully with your own UI messaging.
Configure the drop-in widget declaratively
Your pk_live_ public key. Safe to ship in client-side React code.
The agent that answers—e.g. agent_123. Point different pages at different agents.
Where the floating button sits, such as bottom-right or bottom-left.
Set light or dark theme and an accent color like #4F46E5 to match your brand.
A callback that fires when the call ends—route to analytics, show a survey, or update state.
The underlying agent supports 24+ languages, so one component serves a global user base.
Skip npm entirely if you prefer
Create React App / Vite
Add the one-line <script src="https://app.edesy.ai/widget/voice-widget.js" data-api-key="wk_live_xxx" async></script> to public/index.html before </body>. Note the script tag uses a wk_live_ widget key.
Next.js App Router
Use next/script in app/layout.tsx (a client component with strategy="afterInteractive") to inject the same widget across every route.
Ship It
The floating voice button appears automatically—no components to mount, no state to manage.
Voice AI inside your product
Let logged-in users speak queries instead of typing—wire useEdesy() into your existing UI.
Voice help desks and knowledge lookups embedded directly in your admin panels.
Voice product search and support inside your Next.js storefront.
Progressive web apps get real-time voice without shipping a native app.
Authenticated portals gain voice support with full context and CRM logging.
Wrap the hook in your own component library so voice matches your design tokens everywhere.
Real implementations in production
"We dropped <EdesyWidget /> into our Next.js dashboard in an afternoon. Users now talk to our agent without leaving the app."
Shipped in a Day
SaaS Platform
Engineering
"The useEdesy() hook let us build a fully custom voice UI that matches our design system—start, transcript, and duration were all we needed."
Fully Custom UI
B2B Startup
Frontend Lead
"For our marketing site we just used the script tag with next/script. Same agent, zero component wiring."
Two Paths, One Agent
Developer Tools
Engineering
Common developer questions
Complete your app's voice AI
AI-powered phone calls from ₹6/min — or bring your own AI keys and pay just ₹1.5/min platform fee
Install the SDK or paste the script. Real-time voice in minutes.
Every business is unique. Let's discuss your specific needs and create a pricing plan that works for you.
Custom pricing based on your needs
No hidden fees or surprises
Flexible payment options
Volume discounts available
Free consultation & demo
30-day money-back guarantee
Our team will get back to you within 24 hours with a personalized pricing proposal
Or reach out directly:
Trusted by businesses worldwide
More AI voice agent resources
Real demo calls showcasing low latency and natural conversations in multiple Indian languages
AI voice agent qualifying B2B leads for corporate gifting. Ultra-low latency with 1-2 second response time. Bilingual conversation in Hindi and English.
Audio player powered by Google Drive
Open in DriveAI voice agent handling admission inquiries and appointment booking for educational institutes in Malayalam language.
Audio player powered by Google Drive
Open in DriveAI voice agent handling admission inquiries and appointment booking for educational institutes in Tamil language.
Audio player powered by Google Drive
Open in DriveAI voice agent qualifying leads for solar installation company in Assamese language. Natural conversation flow with product inquiry handling.
Audio player powered by Google Drive
Open in DriveAI voice bot helping patients book hospital appointments in Bengali. Natural conversation with availability checking and confirmation.
Audio player powered by Google Drive
Open in DriveAI voice bot helping patients book hospital appointments in Hindi. Handles doctor selection, time slot booking, and confirmation.
Audio player powered by Google Drive
Open in DriveAI voice bot helping patients book hospital appointments in Telugu. Natural conversation flow for healthcare scheduling.
Audio player powered by Google Drive
Open in DriveStart from $0.04/min - 60% cheaper than alternatives