Enable Transcription and Summarisation

Method 1: Dashboard Implementation

You can enable transcription for all the rooms under a particular template.

1. Access an existing template via the sidebar.
2. Navigate to the Transcription (Beta) tab in the template configuration.
3. Enable the Transcribe Recordings toggle. This will also enable the Room Composite Recording (if not already enabled) under the Recording tab.
4. Enable the Summarise Transcripts toggle. This will take the default settings for summary.
5. Save the configuration.
6. Join a room to initiate a session. Start recording using the SDK or recording API. If it's your first time joining a 100ms room, you'll find the option to Start Recording in the created room. For more information on creating room templates, refer to this documentation.

Advanced Transcription Settings

When you enable the Transcribe Recordings toggle, you will observe an accordion with Advanced Transcription Settings.

• Roles to be Transcribed: Selection is currently disabled. It reflects the same role as set in Room Composite Recording configurations as transcription is supported only with recording. To transcribe other roles, update Roles to be Recorded in Room Composite Recording under the Recording tab.
• Custom Vocabulary: Add non-dictionary words which are expected to be spoken to enhance recognition. Useful for names, abbreviations, slang, technical jargon, and more.

{
 "transcription": {
   "outputModes": ["txt", "srt","json"],
   "customVocabulary": [],
   "summary": {
     "enabled": true,
     "context": "",
     "sections": [
       {
         "title": "Agenda",
         "format": "bullets"
       },
       {
         "title": "Key Points Discussed",
         "format": "bullets"
       },
       {
         "title": "Follow Up Action Items",
         "format": "bullets"
       },
       {
         "title": "Short Summary",
         "format": "paragraph"
       }
     ],
     "temperature": 0.5
   }
 }
}

Method 2: Recording API

You can refer to our Recording API documentation to start recording.

1. You are required to mark the transcription enable flag in the request as true to transcribe unless you’ve already enabled transcription for the given room template. Refer Method 1.
2. You can override the transcription and summary settings given in the policy when starting the recording through the Recording API.
3. If no input is given, the API will pick up the transcription configuration from the template policy.

Method 3: Policy API

You can refer to our Policy API documentation to work with various aspects of creating and updating the template.

John: Hello, hello, hello! How's your day been?

Sarah: Hey, long time no see! What have you been up to?

1
00:00:01,010 --> 00:00:12,870
John: Hello, hello, hello! How's your day been?

2
00:00:14,230 --> 00:00:17,390
Sarah: Hey, long time no see! What have you been up to?

{
  "words": [
    {
      "word": "Hello",
      "name": "John",
      "peer_id": "cf348192-f1d5-4cdb-9eb3-b62c2649e419",
      "start_time": "1010",
      "end_time": "1570"
    },
	.
	.
    {
      "word": "Hey",
      "name": "Sarah",
      "peer_id": "05292829-3603-4a64-be91-5a46abdbd5af",
      "start_time": "14230",
      "end_time": "14430"
    },
	.
	.
  ],
  "sentences": [
    {
      "sentence": "Hello, hello, hello! How's your day been?",
      "name": "John",
      "peer_id": "cf348192-f1d5-4cdb-9eb3-b62c2649e419",
      "start_time": "1010",
      "end_time": "12870"
    },
    {
      "sentence": "Hey, long time no see! What have you been up to?",
      "name": "Sarah",
      "peer_id": "05292829-3603-4a64-be91-5a46abdbd5af",
      "start_time": "14230",
      "end_time": "17390"
    }
  ]
}

{
  "summary": {
    "sections": [
      {
        "title": "Speakers",
        "format": "bullets",
        "bullets": [ "John", "Sarah" ],
        "paragraph": ""
      },
      {
        "title": "Agenda",
        "format": "bullets",
        "bullets": [ "Agenda item 1", "Agenda item 2" ],
        "paragraph": ""
      },
      {
        "title": "Key Points Discussed",
        "format": "bullets",
        "bullets": [ "Key Point 1", "Key Point 2" ],
        "paragraph": ""
      },
      {
        "title": "Follow-up Action Items",
        "format": "bullets",
        "bullets": [ "Follow-up Action Item 1", "Follow-up Action Item 2"],
        "paragraph": ""
      },
      {
        "title": "Short Summary",
        "format": "paragraph",
        "bullets": [],
        "paragraph": "Short summary of the meeting here"
      }
    ]
  }
}

Method 1: Dashboard

Once you’ve recorded a session with transcription and summary enabled, you can expect recording assets to be ready within 20% of the recording duration time period.

To access transcripts and summaries on the dashboard:

1. Navigate to the Sessions tab in the sidebar to view previous sessions.
2. Locate the session with transcription enabled. The Recording Status column will indicate the status of the recording.
3. Click on the Completed status of the chosen session ID.
4. This will open the Session Details page. Access the Recording Log to find the available assets and view them.
5. Click on View Assets to open a pop-up with pre-signed URLs for the recording, chat, transcripts, and summary.

Method 2: Webhooks

As soon as the transcription is completed, the webhook containing the asset type, id, path and the pre-signed URL to the asset itself (transcript, summary) will be sent to the configured webhook URL.

1. Learn to configure the webhook using this documentation.
2. Transcription specific webhook events can be found here.

Method 3: Recording Assets API

You can always use 100ms’ Recording Assets API to access the transcripts and summaries files. Refer to this documentation.