Back to Runanywhere Sdks

RunAnywhere Flutter SDK

sdk/runanywhere-flutter/packages/runanywhere/README.md

0.20.113.9 KB
Original Source

RunAnywhere Flutter SDK

Privacy-first, on-device AI SDK for Flutter. Run LLMs, Speech-to-Text, Text-to-Speech, and Voice AI directly on user devices.

Installation

Step 1: Add packages to pubspec.yaml:

yaml
dependencies:
  runanywhere: ^0.20.11
  runanywhere_onnx: ^0.20.11      # STT, TTS, VAD
  runanywhere_llamacpp: ^0.20.11  # LLM text generation

Step 2: Configure platforms (see below).


iOS Setup (Required)

After adding the packages, you must update your iOS Podfile for the SDK to work.

1. Update ios/Podfile

Make these two critical changes:

ruby
# Change 1: Set minimum iOS version to 17.5
platform :ios, '17.5'

# ... (keep existing flutter_root function and setup) ...

target 'Runner' do
  # Change 2: Add static linkage - THIS IS REQUIRED
  use_frameworks! :linkage => :static

  flutter_install_all_ios_pods File.dirname(File.realpath(__FILE__))
end

post_install do |installer|
  installer.pods_project.targets.each do |target|
    flutter_additional_ios_build_settings(target)
    target.build_configurations.each do |config|
      config.build_settings['IPHONEOS_DEPLOYMENT_TARGET'] = '17.5'
      # Required for microphone permission (STT/Voice features)
      config.build_settings['GCC_PREPROCESSOR_DEFINITIONS'] ||= [
        '$(inherited)',
        'PERMISSION_MICROPHONE=1',
      ]
    end
  end
end

Important: Without use_frameworks! :linkage => :static, you will see "symbol not found" errors at runtime.

For a pub.dev dependency, CocoaPods downloads the version-matched RACommons XCFramework and verifies its immutable SHA-256 checksum automatically. Source checkouts use a locally staged framework when present.

2. Update ios/Runner/Info.plist

Add microphone permission for STT/Voice features:

xml
<key>NSMicrophoneUsageDescription</key>
<string>This app needs microphone access for speech recognition</string>

3. Run pod install

bash
cd ios && pod install

Android Setup

Add microphone permission to android/app/src/main/AndroidManifest.xml:

xml
<uses-permission android:name="android.permission.RECORD_AUDIO" />

Quick Start

dart
import 'package:runanywhere/runanywhere.dart';
import 'package:runanywhere_onnx/runanywhere_onnx.dart';
import 'package:runanywhere_llamacpp/runanywhere_llamacpp.dart';

void main() async {
  WidgetsFlutterBinding.ensureInitialized();

  // Initialize SDK and register backends
  await RunAnywhere.initialize();
  await Onnx.register();
  await LlamaCpp.register();

  runApp(MyApp());
}

Text Generation (LLM)

dart
final stream = RunAnywhere.llm
    .generateStream('Tell me a joke', LLMGenerationOptions(maxTokens: 128));
await for (final event in stream) {
  if (event.isFinal) break;
  if (event.token.isNotEmpty) print(event.token);
}

Speech-to-Text

dart
final result = await RunAnywhere.stt.transcribe(audioData);
print(result.text);

Platform Support

PlatformMinimum Version
iOS17.5+
AndroidAPI 24+

Documentation

License

RunAnywhere License (Apache 2.0 based, with additional commercial-use terms). See LICENSE.

Commercial licensing: [email protected]