React Native

React Native SDK

Real-time AI voice agent calls inside your iOS & Android app with @telenow/react-native. The control plane, codecs, and jitter buffer run in JS (shared with @telenow/client); a small native module does only mic capture + PCM playback in the platform's voice-communication mode, so hardware echo cancellation and noise suppression are on automatically — speakerphone works without the agent hearing itself.

npm i @telenow/react-native @telenow/client
cd ios && pod install        # autolinks the native TelenowAudio module

Before you start

An agent (dashboard → Agents) and its agent ID.
Authorization — recommended: your backend mints a session with an org API key via createWeb / init_web_call and hands { sessionId, websocketUrl } to the app. Alternatives: the agent's published publicSlug or an ephemeral client token.
Microphone permission:
- iOS — Info.plist:
```
<key>NSMicrophoneUsageDescription</key>
<string>Voice calls with our assistant</string>
```
- Android — <uses-permission android:name="android.permission.RECORD_AUDIO" /> in the manifest and a runtime request (PermissionsAndroid.request) before start().

Quickstart

import { TelenowCall } from '@telenow/react-native';

const call = new TelenowCall({
  session,                    // { sessionId, websocketUrl } from YOUR backend (recommended)
  // publicSlug: 'my-agent',  // or: published agent, no auth
  baseUrl: 'https://api.telenow.ai',
});

call.onState = (s) => setCallState(s);   // connecting | live | reconnecting | ended | error
call.onTranscript = (role, text) => append({ role, text });

await call.start();     // starts native audio + connects → live
call.setMuted(true);
call.stop();

Options reference

Option	Type	Default	What it does
`session`	`{ sessionId, websocketUrl }`	—	Backend-minted session — skips on-device init (recommended).
`publicSlug`	`string`	—	Published agent, no auth.
`token`	`string`	—	Ephemeral client token.
`baseUrl`	`string`	`''`	API origin, e.g. `https://api.telenow.ai`.
`variables`	`Record<string,string>`	—	Context variables — or bake them into the minted session (tamper-proof).
`uplinkEncoding`	`'mulaw' \| 'pcm16'`	`'mulaw'`	Wire format — keep the default.
`reconnect`	`{ maxAttempts?, baseDelayMs?, maxDelayMs?, jitter? }`	6 / 500 / 10000 / 0.3	Backoff after network drops.

Callbacks: onState(state), onTranscript(role, text). Methods: start(): Promise<void>, stop(), setMuted(boolean).

What the SDK handles

Echo & noise — iOS AVAudioSession voice-chat mode (VoiceProcessingIO), Android VOICE_COMMUNICATION source: hardware AEC/NS/AGC. Agent playback is routed through the voice-processing unit so the echo canceller removes the agent's own voice from the mic.
Barge-in — interrupting the agent flushes queued audio instantly.
Reconnect — drops retry with backoff while audio keeps running.
Latency pings — answered automatically for your analytics.

Troubleshooting

Symptom	Fix
`TelenowAudio is null`	Autolinking didn't run — `pod install` (iOS) / clean Gradle sync (Android), then rebuild the app (a JS reload isn't enough after installing).
Silent on Android	`RECORD_AUDIO` runtime permission not granted before `start()`.
Silent on iOS simulator	Test audio on a real device — simulator routing is unreliable.
401/403 at start	Bad/expired credential, or API access is off on the agent's Publish tab.
400 naming a variable	A required context variable wasn't passed.
Echo on speakerphone	Keep playback inside the SDK — it runs through the echo canceller.

Other mobile stacks

Native Swift, Kotlin/Android, and Flutter SDKs are coming soon. Until then: embed the hosted widget or public page in a web view, or drive everything over the REST API (your agent's Publish tab has copy-paste cURL, Node, Python, and Rust samples).