Transcribe Video

Creates a new transcription job for video content.

Note: For most use cases, you should use the /describe endpoint instead. This API will be deprecated in the future and only supports speech level understanding.

POST /transcribe

Create a new transcription job

cURL

curl --request POST \
  --url https://api.cloudglue.dev/v1/transcribe \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "url": "<string>",
  "enable_summary": true,
  "enable_speech": true,
  "enable_visual_scene_description": true,
  "enable_scene_text": true,
  "enable_audio_description": true,
  "include_metadata": false,
  "segmentation_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a"
}
'

import requests

url = "https://api.cloudglue.dev/v1/transcribe"

payload = {
    "url": "<string>",
    "enable_summary": True,
    "enable_speech": True,
    "enable_visual_scene_description": True,
    "enable_scene_text": True,
    "enable_audio_description": True,
    "include_metadata": False,
    "segmentation_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a"
}
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({
    url: '<string>',
    enable_summary: true,
    enable_speech: true,
    enable_visual_scene_description: true,
    enable_scene_text: true,
    enable_audio_description: true,
    include_metadata: false,
    segmentation_id: '3c90c3cc-0d44-4b50-8888-8dd25736052a'
  })
};

fetch('https://api.cloudglue.dev/v1/transcribe', 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.cloudglue.dev/v1/transcribe",
  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([
    'url' => '<string>',
    'enable_summary' => true,
    'enable_speech' => true,
    'enable_visual_scene_description' => true,
    'enable_scene_text' => true,
    'enable_audio_description' => true,
    'include_metadata' => false,
    'segmentation_id' => '3c90c3cc-0d44-4b50-8888-8dd25736052a'
  ]),
  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.cloudglue.dev/v1/transcribe"

	payload := strings.NewReader("{\n  \"url\": \"<string>\",\n  \"enable_summary\": true,\n  \"enable_speech\": true,\n  \"enable_visual_scene_description\": true,\n  \"enable_scene_text\": true,\n  \"enable_audio_description\": true,\n  \"include_metadata\": false,\n  \"segmentation_id\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\"\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.cloudglue.dev/v1/transcribe")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"url\": \"<string>\",\n  \"enable_summary\": true,\n  \"enable_speech\": true,\n  \"enable_visual_scene_description\": true,\n  \"enable_scene_text\": true,\n  \"enable_audio_description\": true,\n  \"include_metadata\": false,\n  \"segmentation_id\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.cloudglue.dev/v1/transcribe")

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  \"url\": \"<string>\",\n  \"enable_summary\": true,\n  \"enable_speech\": true,\n  \"enable_visual_scene_description\": true,\n  \"enable_scene_text\": true,\n  \"enable_audio_description\": true,\n  \"include_metadata\": false,\n  \"segmentation_id\": \"3c90c3cc-0d44-4b50-8888-8dd25736052a\"\n}"

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

200

{
  "job_id": "<string>",
  "url": "<string>",
  "created_at": 123,
  "transcribe_config": {
    "enable_summary": true,
    "enable_speech": true,
    "enable_visual_scene_description": true,
    "enable_scene_text": true
  },
  "data": {
    "content": "<string>",
    "title": "<string>",
    "summary": "<string>",
    "segment_summary": [
      {
        "title": "<string>",
        "summary": "<string>",
        "start_time": 123,
        "end_time": 123
      }
    ],
    "visual_scene_description": [
      {
        "text": "<string>",
        "start_time": 123,
        "end_time": 123
      }
    ],
    "scene_text": [
      {
        "text": "<string>",
        "start_time": 123,
        "end_time": 123
      }
    ],
    "speech": [
      {
        "speaker": "<string>",
        "text": "<string>",
        "start_time": 123,
        "end_time": 123,
        "words": [
          {
            "word": "<string>",
            "start_time": 123,
            "end_time": 123
          }
        ]
      }
    ],
    "audio_description": [
      {
        "text": "<string>",
        "start_time": 123,
        "end_time": 123
      }
    ]
  },
  "error": "<string>",
  "file": {
    "id": "<string>",
    "uri": "<string>",
    "bytes": 123,
    "created_at": 123,
    "filename": "<string>",
    "metadata": {},
    "media_info": {
      "duration_seconds": 123,
      "width": 123,
      "height": 123,
      "sample_rate": 123,
      "channels": 123,
      "bitrate": 123,
      "format": "<string>",
      "has_audio": true
    },
    "video_info": {
      "duration_seconds": 123,
      "height": 123,
      "width": 123,
      "format": "<string>",
      "has_audio": true
    },
    "thumbnail_url": "<string>",
    "source_metadata": {
      "source_type": "grain",
      "grain_recording_id": "<string>",
      "title": "<string>",
      "start_datetime": "2023-11-07T05:31:56Z",
      "end_datetime": "2023-11-07T05:31:56Z",
      "duration_ms": 123,
      "grain_url": "<string>",
      "thumbnail_url": "<string>",
      "tags": [
        "<string>"
      ],
      "teams": [
        {
          "id": "<string>",
          "name": "<string>"
        }
      ],
      "meeting_type": {
        "id": "<string>",
        "name": "<string>",
        "scope": "<string>"
      },
      "participants": [
        {
          "id": "<string>",
          "name": "<string>",
          "email": "<string>",
          "confirmed_attendee": true,
          "hs_contact_id": "<string>"
        }
      ],
      "highlights": [
        {}
      ],
      "ai_summary": {
        "text": "<string>"
      },
      "ai_action_items": [
        {
          "timestamp_ms": 123,
          "text": "<string>",
          "assignee": {
            "id": "<string>",
            "name": "<string>",
            "user_id": "<string>"
          }
        }
      ],
      "ai_template_sections": [
        {}
      ],
      "calendar_event": {
        "ical_uid": "<string>"
      },
      "hubspot": {
        "hubspot_company_ids": [
          "<string>"
        ],
        "hubspot_deal_ids": [
          "<string>"
        ]
      }
    }
  }
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}

{
  "error": "<string>"
}

Authorizations

Authorization · string · header · required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

Transcription job parameters

url · string · required

Input video URL. Supports URIs of files uploaded to Cloudglue Files endpoint, public YouTube video URLs, public TikTok video URLs, public Loom share URLs, public HTTP URLs, and files which have been granted access to Cloudglue via data connectors.

Note that YouTube videos are currently limited to speech level understanding only. Public TikTok video URLs will be scraped and stored automatically — subject to charges. For files via our Data connectors, see our documentation on data connectors for setup information.

enable_summary · boolean

Whether to generate video-level and segment-level (moment-level) summaries and titles

enable_speech · boolean

Whether to generate speech transcript

enable_visual_scene_description · boolean

Whether to generate visual scene description

enable_scene_text · boolean

Whether to generate scene text extraction

enable_audio_description · boolean

Whether to generate audio description

thumbnails_config · object

Show child attributes

include_metadata · boolean · default: false

Include the file's user-defined metadata and source metadata on the returned file object.

segmentation_id · string<uuid>

Segmentation job id to use. If not provided will use default to uniform 20s segmentation. Cannot be provided together with segmentation_config.

segmentation_config · object

Configuration for video segmentation. Cannot be provided together with segmentation_id.

Show child attributes

Response

200

application/json

Successful response

job_id · string · required

status · enum<string> · required

Available options: pending, processing, completed, failed, not_applicable

url · string

The URL of the processed video

created_at · integer

Unix timestamp in milliseconds when the job was created

transcribe_config · object

Configuration for rich transcription from videos

Show child attributes

data · object

Show child attributes

error · string

Error message if status is 'failed'

file · object

The file this document describes. metadata and source_metadata are only included when include_metadata is true.

Show child attributes