Integration Apps

What Are Integration Apps?

Integration apps allow Omi to interact with external services by sending data to your webhook endpoints. Unlike prompt-based apps, these require you to host a server.

Memory Triggers

Run code when a memory is created

Real-Time Transcript

Process live transcripts as they happen

Audio Streaming

Receive raw audio bytes for custom processing

Memory Creation Triggers

These apps are activated when Omi creates a new memory, allowing you to process or store the data externally.

How It Works

User completes a conversation
Omi processes and creates a memory
Your webhook receives the complete memory object
Your server processes and responds

The webhook receives the full conversation data including transcript, structured summary, action items, and metadata.

Example Use Cases

Slack Integration: Post conversation summaries to team channels
CRM Updates: Log customer interactions automatically
Project Management: Create tasks in Notion, Asana, or Jira
Knowledge Base: Build a searchable archive of conversations
Analytics: Track conversation patterns and insights

Video Tutorial

Running FastAPI locally (no cloud deployment):

Webhook Payload

Your endpoint receives a POST request with the memory object: POST /your-endpoint?uid=user123

{
  "id": "memory_abc123",
  "created_at": "2024-07-22T23:59:45.910559+00:00",
  "started_at": "2024-07-21T22:34:43.384323+00:00",
  "finished_at": "2024-07-21T22:35:43.384323+00:00",
  "transcript_segments": [
    {
      "text": "Let's discuss the project timeline.",
      "speaker": "SPEAKER_00",
      "speakerId": 0,
      "is_user": false,
      "start": 10.0,
      "end": 15.0
    }
  ],
  "structured": {
    "title": "Project Timeline Discussion",
    "overview": "Brief overview of the conversation...",
    "emoji": "📅",
    "category": "work",
    "action_items": [
      {
        "description": "Send project proposal by Friday",
        "completed": false
      }
    ],
    "events": []
  },
  "apps_response": [],
  "discarded": false
}

Check out the Notion CRM Example for a complete implementation.

Real-Time Transcript Processors

Process conversation transcripts as they occur, enabling real-time analysis and actions.

How It Works

User starts speaking
Omi transcribes in real-time
Your webhook receives transcript segments as they’re created
Your server processes and can trigger immediate actions

Segments arrive in multiple calls as the conversation unfolds, allowing for live reactions.

Example Use Cases

Live Coaching: Provide real-time feedback during presentations
Fact-Checking: Verify claims as they’re made
Smart Home: Trigger actions based on spoken commands
Sentiment Analysis: Monitor emotional tone in real-time
Translation: Live translation of conversations

Video Tutorial

Webhook Payload

Your endpoint receives transcript segments with session context: POST /your-endpoint?session_id=abc123&uid=user123

[
  {
    "text": "I think we should prioritize the mobile app.",
    "speaker": "SPEAKER_00",
    "speakerId": 0,
    "is_user": false,
    "start": 10.0,
    "end": 15.0
  },
  {
    "text": "Agreed, let's start with iOS.",
    "speaker": "SPEAKER_01",
    "speakerId": 1,
    "is_user": true,
    "start": 16.0,
    "end": 18.0
  }
]

Implementation Tips

Real-time processors require careful design to avoid performance issues.

Use session_id

Track context across multiple calls using the session_id parameter

Avoid Redundancy

Implement logic to prevent processing the same segments twice

Accumulate Context

Build complete conversation context by storing segments

Handle Errors

Fail gracefully - don’t block transcription with slow processing

See the Real-time News Checker Example for a complete implementation.

Real-Time Audio Bytes

Stream raw audio bytes from Omi directly to your endpoint for custom audio processing.

How It Works

User speaks into Omi device
Raw PCM audio is streamed to your endpoint
Your server processes the audio bytes directly
Handle as needed (custom STT, VAD, feature extraction, etc.)

Unlike transcript processors, you receive the actual audio data, not text.

Example Use Cases

Custom ASR: Use your own speech recognition models
Voice Activity Detection: Implement custom VAD logic
Audio Features: Extract spectrograms, embeddings, or other features
Recording: Store raw audio for later processing
Real-time Translation: Feed audio to translation services

Technical Details

Setting	Value
Trigger Type	`audio_bytes`
HTTP Method	POST
Content-Type	`application/octet-stream`
Audio Format	PCM16 (16-bit little-endian)
Bytes per Sample	2

Request format: POST /your-endpoint?sample_rate=16000&uid=user123 Body contains raw PCM16 audio bytes.

To produce a playable WAV file, prepend a WAV header and concatenate the received chunks.

Configuring Delivery Frequency

You can control how often audio is sent via the Omi app Developer Settings:

url,seconds

For example: https://your-endpoint.com/audio,5 sends audio every 5 seconds.

For a complete implementation, see the Audio Streaming Guide.

Creating an Integration App

Choose Your Trigger Type

Decide which integration type(s) you need:

Memory Trigger: Process completed conversations
Real-Time Transcript: React to live speech
Audio Bytes: Process raw audio

Set Up Your Endpoint

Create a webhook endpoint that can receive POST requests. For testing, use webhook.site or webhook-test.com.Your endpoint should:

Accept POST requests
Parse JSON body (or binary for audio)
Read uid from query parameters
Return 200 OK quickly

Implement Your Logic

Process the incoming data and integrate with external services.Example (Python/FastAPI):

from fastapi import FastAPI, Request

app = FastAPI()

@app.post("/webhook")
async def handle_memory(request: Request, uid: str):
    memory = await request.json()
    # Process memory data
    await send_to_slack(memory["structured"]["title"])
    return {"status": "ok"}

Test Your Integration

Use Developer Mode to test without creating new memories (see testing section below)

Submit Your App

Publish through the Omi mobile app

Testing Your Integration

Enable Developer Mode

Open Omi app → Settings → Enable Developer Mode → Developer Settings

Set Webhook URL

Memory Triggers: Enter URL in “Memory Creation Webhook”
Real-Time: Enter URL in “Real-Time Transcript Webhook”

Test Memory Triggers

Go to any memory → Tap 3-dot menu → Developer Tools → Trigger webhook with existing data

Test Real-Time

Start speaking - your endpoint receives updates immediately

Use webhook.site to see exactly what data Omi sends before writing any code.

App Submission Fields

When submitting your integration app:

Field	Required	Description
Webhook URL	Yes	Your POST endpoint for receiving data
Setup Completed URL	No	GET endpoint returning `{"is_setup_completed": boolean}`
Auth URL	No	URL for user authentication (uid appended automatically)
Setup Instructions	No	Text or link explaining how to configure your app

Setup Instructions Best Practices

Step-by-Step Guide

Clear numbered instructions for configuration

Screenshots

Visual aids for complex setup steps

Authentication Flow

If required, explain how to connect accounts

Troubleshooting

Common issues and how to resolve them

When users open your setup links, Omi automatically appends a uid query parameter. Use this to associate credentials with specific users.

Developer API

Access your own personal Omi data programmatically

Data Import APIs

Create conversations and memories via REST API

Audio Streaming Guide

Detailed guide for processing raw audio bytes

Chat Tools

Add custom tools users can invoke in chat

OAuth Setup

Add authentication flows to your apps

Notifications

Send push notifications from your app

Prompt-Based Apps

Create apps without hosting a server

Apps Introduction

Overview of all app types

Get Started

Core Development

Developer API

MCP Integration

Build Apps

Hardware

DIY Guide

Info

​What Are Integration Apps?

Memory Triggers

Real-Time Transcript

Audio Streaming

​Memory Creation Triggers

​Webhook Payload

​Real-Time Transcript Processors

​Webhook Payload

​Implementation Tips

Use session_id

Avoid Redundancy

Accumulate Context

Handle Errors

​Real-Time Audio Bytes

​Technical Details

​Configuring Delivery Frequency

​Creating an Integration App

​Testing Your Integration

​App Submission Fields

​Setup Instructions Best Practices

Step-by-Step Guide

Screenshots

Authentication Flow

Troubleshooting

​Related Documentation

Developer API

Data Import APIs

Audio Streaming Guide

Chat Tools

OAuth Setup

Notifications

Prompt-Based Apps

Apps Introduction

What Are Integration Apps?

Memory Creation Triggers

Webhook Payload

Real-Time Transcript Processors

Webhook Payload

Implementation Tips

Real-Time Audio Bytes

Technical Details

Configuring Delivery Frequency

Creating an Integration App

Testing Your Integration

App Submission Fields

Setup Instructions Best Practices

Related Documentation