Wiro Realtime for Flutter: Voice AI Example for Android and iOS
Realtime voice AI for Android and iOS in Flutter and Dart: live conversation, speech-to-text and text-to-speech with the Wiro AI API.
Wiro Realtime for Flutter is the official open-source example for
building realtime voice AI into Android and iOS apps with Flutter, Dart
and the Wiro AI API. Its three tabs stream audio over WebSocket for a
live speech-to-speech conversation with barge-in, live speech-to-text
from the microphone, and text-to-speech playback. The core/ layer
(auth, network, realtime, audio) has no dependency on any feature, so
you can lift it into your own app.
What's inside
Three realtime audio flows, each a tab in the app, each backed by a live
Wiro AI model over one WebSocket protocol:
| Flow | Model | What it does |
|---|---|---|
| Conversation | openai/gpt-realtime-mini |
Full-duplex voice chat with barge-in |
| Transcription | mistralai/voxtral-mini-4b-realtime-2602 |
Live speech-to-text as you talk |
| Speech | openmoss/moss-tts-realtime or openbmb/voxcpm2 |
Streaming text-to-speech playback |
Features
- Live speech-to-speech conversation with voice activity detection,
barge-in, and a noise gate - Realtime microphone transcription with streaming partial results
- Streaming text-to-speech with bounded PCM playback
- One native audio graph for capture and playback, so the OS echo
canceller (AEC) actually works (see
packages/wiro_voice_engine) - Signed REST Run requests and the full Wiro AI realtime WebSocket
protocol - Bounded capture/playback queues, safe PCM overflow shedding, audio
route and interruption handling - Cross-feature guard so two tabs never hold the microphone at once
- Automatic reconnect to the same task on socket drops, with a bounded
restart budget - Session lifecycle fully covered by tests, so no device is needed to
verify the plumbing
Requirements
- Flutter stable with Dart
3.13.1or newer - A physical Android or iOS device (simulators have no usable
microphone path) - A Wiro AI project and API key
The iOS project uses Swift Package Manager: there is no Podfile and no
CocoaPods setup to run. Use a Flutter version with SPM support enabled.
The project ships without a signing team: open ios/Runner.xcworkspace
once and pick yours under Runner → Signing & Capabilities before the
first device run.
Run
flutter pub get
flutter run --dart-define=WIRO_API_KEY=YOUR_API_KEYFor signature-based Wiro AI projects, also pass the secret:
flutter run \
--dart-define=WIRO_API_KEY=YOUR_API_KEY \
--dart-define=WIRO_API_SECRET=YOUR_API_SECRETLeave WIRO_API_SECRET out for API-key-only projects. The app fails
before runApp when WIRO_API_KEY is missing.
Credentials warning: values supplied through
--dart-defineare
compiled into the binary and are for local development only. Never
distribute builds containing real credentials: production apps should
authenticate through a controlled backend or a short-lived credential
flow.
Make it yours
lib/app/config/conversation_config.dart
holds the persona, the voice, the model, and the session time limit.
Editing that one file is the whole of turning this example into a
product.
static const String persona = '...who the assistant is...';
static const String voice = 'marin';
static const Duration maxSessionDuration = Duration(minutes: 10);Common changes:
- Give the assistant a job: rewrite
persona. - Change the voice: set
voiceto any option the model catalog
lists. - Tune the engineering parameters:
parametersoverrides the
catalog defaults for turn detection, audio formats, and rates. - Ship only the conversation: delete
lib/features/speech_to_text/andlib/features/text_to_speech/
(plus theirtest/features/folders), then remove the two
NavigationDestinations from
lib/features/realtime_home/view/realtime_home_view.dart.core/is
untouched.
How a conversation runs
REST: https://api.wiro.ai/v1
WebSocket: wss://socket.wiro.ai/v1
Run: POST /Run/{owner}/{model}
POST /Run/{owner}/{model}returns a task id and a task token.- A WebSocket opens and subscribes with
{ "type": "task_info", "tasktoken": "..." }. - After
task_stream_ready, 20 ms PCM chunks stream up as
UTF8(tasktoken + "|") + pcm_bytes; audio and transcripts stream
back. task_session_endcloses the session. The app sends it on leave
or whenmaxSessionDurationruns out.
Audio is signed 16-bit PCM, 24 kHz, mono, little-endian on both sides.
Authentication is x-api-key alone, or x-api-key + x-nonce +
x-signature where the signature is
HMAC-SHA256(key = API_KEY, message = API_SECRET + NONCE).
Project layout
lib/
app/ shell, theme, layout tokens, config, shared widgets
core/ reusable Wiro AI plumbing: auth, network, realtime, audio
features/ one folder per tab: view/, view_model/, service/
packages/
wiro_voice_engine/ native AEC audio bridge (AVAudioEngine / AudioRecord)
core/ has no dependency on any feature and covers the whole Wiro AI
integration, so it is the part worth lifting into your own app.
Tests
flutter analyze
flutter testTests mirror lib/ and ship fakes for audio, network, and the socket,
so the entire session lifecycle runs without a device. CI runs the same
two commands, plus flutter analyze for packages/wiro_voice_engine,
on pushes to main and on pull requests.
Contributing
Read CONTRIBUTING.md before opening a pull request.
To report a security problem, follow SECURITY.md
instead of opening a public issue.
Documentation
- Realtime voice guide
- Wiro AI documentation
- Available models
- Same example on other platforms:
Swift ·
Kotlin ·
React Native - Dart-QuickStart:
Wiro AI SDK for Dart and Flutter, published aswiroon pub.dev
More from Wiro AI
| Repository | What it is |
|---|---|
| Wiro-MCP | Official MCP server for Wiro AI, @wiro-ai/wiro-mcp on npm |
| Wiro-LLM | Vercel AI SDK provider for chat, images, speech, transcription and video, @wiro-ai/wiro-llm on npm |
| Wiro-Chromium-Extension | Wiro AI extension for Chrome, Edge, Opera and Brave |
| Wiro-Firefox-Extension | Wiro AI add-on for Firefox |
| Wiro-Safari-Extension | Wiro AI extension for Safari on the Mac |
| Wiro-Plugin | Wiro AI plugin for Cursor, Claude Code, Gemini CLI, Devin, Antigravity and Kiro |
| Wiro-Skills | Agent skills for images, image edits, video, music, speech, transcripts, 3D and model search |
| Swift-QuickStart | WiroKit, the Wiro AI SDK for iOS |
| Kotlin-QuickStart | WiroKit, the Wiro AI SDK for Android |
| Dart-QuickStart | Wiro AI SDK for Dart and Flutter, wiro on pub.dev |
| ReactNative-QuickStart | Wiro AI SDK for React Native and Expo, @wiro-ai/wiro-react-native on npm |
| Swift-Realtime | Realtime voice AI example for iOS |
| Kotlin-Realtime | Realtime voice AI example for Android |
| ReactNative-Realtime | Realtime voice AI example for React Native |
| n8n-nodes-wiro | One Wiro AI node for n8n with a searchable model picker, @wiro-ai/n8n-nodes-wiro on npm |
| Wiro-Dify-Plugin | Wiro AI plugins for Dify: the LLM gateway as a model provider, plus image, video, speech and music tools |
| Wiro-ComfyUI | Wiro AI nodes for ComfyUI |
| Wiro-Hermes | Wiro AI plugins for Hermes Agent: image, video, audio and 3D tools, plus the LLM gateway as a model provider |
| Wiro-Zed | Wiro AI MCP server extension for Zed |
| Wiro-Action | GitHub Action for Wiro AI models and the LLM gateway, on the GitHub Marketplace |
| Wiro-Raycast | Wiro AI extension for Raycast: image and video generation, LLM chat and model search |
| Wiro-WordPress | Wiro AI plugin for WordPress: featured images, image edits, alt text, narration and SEO suggestions |
| Wiro-Obsidian | Wiro AI plugin for Obsidian: images, video, speech, music, transcription and text tools |
| Wiro-Blender | Wiro AI add-on for Blender: text to 3D, image to 3D and textures |
| Wiro-Figma | Wiro AI plugin for Figma: images, vectors, image edits and text |
| Wiro-Next-Starter | Next.js starter for Wiro AI: Playground, image, video and audio tools, and LLM chat, ready for Vercel and Railway |
| Wiro-Docs | Source of the Wiro AI API docs |
| wiroai.github.io | Every open-source project from Wiro AI on one page, with a page for each repository |



