How To: Fetch a Transcript for an Episode

Getting Started

The SeekrAlign Podcast Intelligence API enables users to retrieve a detailed transcript for a specific podcast episode. This API call is essential for analyzing spoken content within an episode, including detecting civility, identifying GARM categories, and segmenting by speaker.

If you need general metadata for an episode, use the Fetch Episode Details API call instead.

Purpose

This API call retrieves transcript data for a specific podcast episode, including timestamps, speaker attribution, and identified GARM classifications. It supports in-depth content analysis and compliance workflows.

API Endpoint

API Reference:
GET Transcript for an Episode

Base URL:
https://services-api.seekr.com/api/v1/podcasts/{podcastId}/episodes/{episodeId}/transcript

Path Parameters

Authentication

All API requests must include an API key for authentication.
Header Format:

Authorization: Bearer <api_key>

Response Format

Responses are returned in JSON format, providing transcript data with speaker attribution and GARM classifications.

Using the Fetch Transcript for an Episode API

Step 1: Identify the Podcast and Episode IDs

• Use the Fetch Podcast Information API to retrieve the podcastId for the show.
• Use the Fetch Episodes from a Podcast API to retrieve the episodeId for the desired episode.

Step 2: Make the API Call

Submit a GET request to the endpoint, including both the podcastId and episodeId in the URL.

Example Request

curl --request GET \
--url https://services-api.seekr.com/api/v1/podcasts/abc123xyz456/episodes/def456uvw789/transcript \
--header 'accept: application/json' \
--header 'authorization: Bearer your_api_key'

Example Response

{
  "apiVersion": "1.0.0",
  "status": 200,
  "results": {
    "episodeId": "def456uvw789",
    "podcastId": "abc123xyz456",
    "transcriptChunks": [
      {
        "civility": "non_severe_attack",
        "garm": [
          {
            "category": "Firearms",
            "level": "high"
          }
        ],
        "speaker": "SPEAKER_03",
        "text": "This is a sample transcript chunk.",
        "timestamp": 123
      },
      {
        "civility": "neutral",
        "garm": [],
        "speaker": "SPEAKER_01",
        "text": "Another part of the transcript.",
        "timestamp": 234
      }
    ]
  }
}

Use Case Examples

Example 1: Analyze Speaker Civility

Objective: Evaluate the civility of speakers in an episode.
Steps:

• Retrieve the transcript using this API call.
• Analyze the civility field for each chunk.
  Result: Identifies sections of the episode that may require editorial review.

Best Practices

1. Leverage Timestamps: Use timestamp data to link transcript content to specific audio segments.
2. Evaluate GARM Classifications: Ensure compliance with industry standards by reviewing flagged categories.
3. Utilize Speaker Attribution: Attribute text to individual speakers for nuanced analysis.

For more details, visit the SeekrAlign API Documentation.

Would you like to proceed with the sixth and final API call?