Create from Transcript Segments

Create a new conversation from structured transcript segments.

This endpoint is for advanced integrations that have speaker diarization and timing information. It processes the transcript segments through the full conversation pipeline.

Transcript Segments:

• text: The text spoken (required)
• speaker: Speaker identifier like ‘SPEAKER_00’, ‘SPEAKER_01’ (default: ‘SPEAKER_00’)
• speaker_id: Numeric speaker ID (auto-calculated from speaker if not provided)
• is_user: Whether this segment is from the user (default: False)
• person_id: ID of known person speaking (optional)
• start: Start time in seconds, e.g., 0.0, 1.5, 60.2 (required)
• end: End time in seconds, e.g., 1.5, 3.0, 65.8 (required)

Other Parameters:

• source: Source of conversation (default: external_integration). Options:
  • omi, friend, openglass, phone, desktop, apple_watch, bee, plaud, frame, etc.
• started_at: When conversation started (defaults to now)
• finished_at: When conversation finished (calculated from last segment if not provided)
• language: Language code (default: ‘en’)
• geolocation: Optional geolocation data

Example:

{
  "transcript_segments": [
    {
      "text": "Hey, how are you doing?",
      "speaker": "SPEAKER_00",
      "is_user": true,
      "start": 0.0,
      "end": 2.5
    },
    {
      "text": "I'm doing great, thanks!",
      "speaker": "SPEAKER_01",
      "is_user": false,
      "start": 2.8,
      "end": 5.2
    }
  ],
  "source": "phone",
  "language": "en"
}

POST /v1/dev/user/conversations/from-segments

Create Conversation From Segments

cURL

curl --request POST \
  --url https://api.omi.me/v1/dev/user/conversations/from-segments \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "transcript_segments": [
    {
      "end": 123,
      "start": 123,
      "text": "<string>",
      "is_user": false,
      "person_id": "<string>",
      "speaker": "SPEAKER_00",
      "speaker_id": 123
    }
  ],
  "client_device_id": "<string>",
  "client_platform": "<string>",
  "client_session_id": "<string>",
  "finished_at": "2023-11-07T05:31:56Z",
  "geolocation": {
    "latitude": 123,
    "longitude": 123,
    "address": "<string>",
    "google_place_id": "<string>",
    "location_type": "<string>"
  },
  "language": "en",
  "source": "phone",
  "started_at": "2023-11-07T05:31:56Z"
}
'

import requests

url = "https://api.omi.me/v1/dev/user/conversations/from-segments"

payload = {
    "transcript_segments": [
        {
            "end": 123,
            "start": 123,
            "text": "<string>",
            "is_user": False,
            "person_id": "<string>",
            "speaker": "SPEAKER_00",
            "speaker_id": 123
        }
    ],
    "client_device_id": "<string>",
    "client_platform": "<string>",
    "client_session_id": "<string>",
    "finished_at": "2023-11-07T05:31:56Z",
    "geolocation": {
        "latitude": 123,
        "longitude": 123,
        "address": "<string>",
        "google_place_id": "<string>",
        "location_type": "<string>"
    },
    "language": "en",
    "source": "phone",
    "started_at": "2023-11-07T05:31:56Z"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    transcript_segments: [
      {
        end: 123,
        start: 123,
        text: '<string>',
        is_user: false,
        person_id: '<string>',
        speaker: 'SPEAKER_00',
        speaker_id: 123
      }
    ],
    client_device_id: '<string>',
    client_platform: '<string>',
    client_session_id: '<string>',
    finished_at: '2023-11-07T05:31:56Z',
    geolocation: {
      latitude: 123,
      longitude: 123,
      address: '<string>',
      google_place_id: '<string>',
      location_type: '<string>'
    },
    language: 'en',
    source: 'phone',
    started_at: '2023-11-07T05:31:56Z'
  })
};

fetch('https://api.omi.me/v1/dev/user/conversations/from-segments', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.omi.me/v1/dev/user/conversations/from-segments",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'transcript_segments' => [
        [
                'end' => 123,
                'start' => 123,
                'text' => '<string>',
                'is_user' => false,
                'person_id' => '<string>',
                'speaker' => 'SPEAKER_00',
                'speaker_id' => 123
        ]
    ],
    'client_device_id' => '<string>',
    'client_platform' => '<string>',
    'client_session_id' => '<string>',
    'finished_at' => '2023-11-07T05:31:56Z',
    'geolocation' => [
        'latitude' => 123,
        'longitude' => 123,
        'address' => '<string>',
        'google_place_id' => '<string>',
        'location_type' => '<string>'
    ],
    'language' => 'en',
    'source' => 'phone',
    'started_at' => '2023-11-07T05:31:56Z'
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.omi.me/v1/dev/user/conversations/from-segments"

	payload := strings.NewReader("{\n  \"transcript_segments\": [\n    {\n      \"end\": 123,\n      \"start\": 123,\n      \"text\": \"<string>\",\n      \"is_user\": false,\n      \"person_id\": \"<string>\",\n      \"speaker\": \"SPEAKER_00\",\n      \"speaker_id\": 123\n    }\n  ],\n  \"client_device_id\": \"<string>\",\n  \"client_platform\": \"<string>\",\n  \"client_session_id\": \"<string>\",\n  \"finished_at\": \"2023-11-07T05:31:56Z\",\n  \"geolocation\": {\n    \"latitude\": 123,\n    \"longitude\": 123,\n    \"address\": \"<string>\",\n    \"google_place_id\": \"<string>\",\n    \"location_type\": \"<string>\"\n  },\n  \"language\": \"en\",\n  \"source\": \"phone\",\n  \"started_at\": \"2023-11-07T05:31:56Z\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.omi.me/v1/dev/user/conversations/from-segments")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"transcript_segments\": [\n    {\n      \"end\": 123,\n      \"start\": 123,\n      \"text\": \"<string>\",\n      \"is_user\": false,\n      \"person_id\": \"<string>\",\n      \"speaker\": \"SPEAKER_00\",\n      \"speaker_id\": 123\n    }\n  ],\n  \"client_device_id\": \"<string>\",\n  \"client_platform\": \"<string>\",\n  \"client_session_id\": \"<string>\",\n  \"finished_at\": \"2023-11-07T05:31:56Z\",\n  \"geolocation\": {\n    \"latitude\": 123,\n    \"longitude\": 123,\n    \"address\": \"<string>\",\n    \"google_place_id\": \"<string>\",\n    \"location_type\": \"<string>\"\n  },\n  \"language\": \"en\",\n  \"source\": \"phone\",\n  \"started_at\": \"2023-11-07T05:31:56Z\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.omi.me/v1/dev/user/conversations/from-segments")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"transcript_segments\": [\n    {\n      \"end\": 123,\n      \"start\": 123,\n      \"text\": \"<string>\",\n      \"is_user\": false,\n      \"person_id\": \"<string>\",\n      \"speaker\": \"SPEAKER_00\",\n      \"speaker_id\": 123\n    }\n  ],\n  \"client_device_id\": \"<string>\",\n  \"client_platform\": \"<string>\",\n  \"client_session_id\": \"<string>\",\n  \"finished_at\": \"2023-11-07T05:31:56Z\",\n  \"geolocation\": {\n    \"latitude\": 123,\n    \"longitude\": 123,\n    \"address\": \"<string>\",\n    \"google_place_id\": \"<string>\",\n    \"location_type\": \"<string>\"\n  },\n  \"language\": \"en\",\n  \"source\": \"phone\",\n  \"started_at\": \"2023-11-07T05:31:56Z\"\n}"

response = http.request(request)
puts response.read_body

200

{
  "discarded": true,
  "id": "<string>",
  "status": "<string>"
}

{
  "detail": "<string>"
}

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>"
    }
  ]
}

Authorizations

Authorization · string · header · required

Send Authorization: Bearer <firebase_id_token>.

Body

application/json

transcript_segments · CreateConversationTranscriptSegment · object[] · required

List of transcript segments with speaker and timing info

Required array length: 1 - 500 elements

Show child attributes

client_device_id · string | null

Capture device id ({platform}_{hash})

client_platform · string | null

Client platform (ios/android/macos)

client_session_id · string | null

Stable client-generated session ID. When provided, retries return the same conversation ID.

Required string length: 1 - 200

finished_at · string<date-time> | null

When conversation finished (calculated from segments duration if not provided)

geolocation · Geolocation · object | null

Geolocation where conversation occurred

Show child attributes

language · string | null · default: en

Language code (ISO 639-1, e.g., 'en', 'es', 'fr')

source · enum<string> | null · default: phone

Source of the conversation (e.g., omi, friend, openglass, phone, external_integration)

Available options: friend, omi, fieldy, bee, plaud, frame, friend_com, apple_watch, phone, phone_call, desktop, openglass, screenpipe, workflow, sdcard, external_integration, limitless, rayban_meta, onboarding, unknown

started_at · string<date-time> | null

When conversation started (defaults to now)

Response

200

application/json

Successful Response

discarded · boolean · required

id · string · required

status · string · required