Get a video transcript

const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};

fetch('https://api.arcmira.com/v1/transcripts/{video_id}', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

{
  "video": {
    "videoId": "<string>",
    "title": "<string>",
    "channelName": "<string>",
    "channelId": "<string>",
    "publishedAt": "<string>",
    "durationSeconds": 123,
    "viewCount": 123
  },
  "segments": [
    {
      "index": 123,
      "start": 123,
      "end": 123,
      "text": "<string>",
      "speaker": 123
    }
  ],
  "speakers": [
    {
      "id": 123,
      "label": "<string>",
      "role": "<string>",
      "confidence": "<string>",
      "voiceRole": "<string>",
      "entity": {
        "id": 123,
        "name": "<string>",
        "slug": "<string>"
      }
    }
  ],
  "annotations": [
    {
      "segmentIndex": 123,
      "charStart": 123,
      "charEnd": 123,
      "entityId": 123,
      "entityType": "<string>",
      "name": "<string>",
      "slug": "<string>"
    }
  ],
  "meta": {
    "diarized": true,
    "locked": true,
    "quote": {
      "quarters": 123,
      "rows": 123
    },
    "revision": "<string>",
    "overLimit": true,
    "devPreview": true,
    "usageLimit": {
      "message": "<string>",
      "ctaLabel": "<string>",
      "ctaHref": "<string>"
    }
  },
  "detected": {
    "people": 123,
    "organizations": 123,
    "products": 123,
    "topics": 123
  },
  "edits": [
    {
      "id": 123,
      "segmentIndex": 123,
      "originalText": "<string>",
      "correctedText": "<string>",
      "status": "<string>",
      "mine": true
    }
  ],
  "speakerIdentifications": [
    {
      "id": 123,
      "speakerId": 123,
      "entityId": 123,
      "entityName": "<string>",
      "status": "<string>"
    }
  ],
  "speakerEdits": [
    {
      "id": 123,
      "seq": 123,
      "editType": "<string>",
      "selection": {
        "startIndex": 123,
        "startChar": 123,
        "endIndex": 123,
        "endChar": 123
      },
      "target": {
        "kind": "<string>",
        "speakerId": 123,
        "label": "<string>",
        "role": "<string>"
      },
      "status": "<string>"
    }
  ],
  "entityTags": [
    {
      "id": 123,
      "seq": 123,
      "segmentIndex": 123,
      "charStart": 123,
      "charEnd": 123,
      "selectedText": "<string>",
      "entity": {
        "id": 123,
        "name": "<string>",
        "slug": "<string>",
        "type": "<string>"
      },
      "status": "<string>"
    }
  ],
  "segmentRewrites": [
    {
      "id": 123,
      "seq": 123,
      "startIndex": 123,
      "endIndex": 123,
      "replacements": [
        {
          "text": "<string>",
          "speaker": 123,
          "start": 123,
          "end": 123
        }
      ],
      "status": "<string>"
    }
  ]
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "doc_url": "<string>",
    "request_id": "<string>",
    "param": "<string>"
  }
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "doc_url": "<string>",
    "request_id": "<string>",
    "param": "<string>"
  }
}

{
  "error": "<string>",
  "quote": {
    "quarters": 123,
    "rows": 123
  }
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "doc_url": "<string>",
    "request_id": "<string>",
    "param": "<string>"
  }
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "doc_url": "<string>",
    "request_id": "<string>",
    "param": "<string>"
  }
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "doc_url": "<string>",
    "request_id": "<string>",
    "param": "<string>"
  }
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "doc_url": "<string>",
    "request_id": "<string>",
    "param": "<string>"
  }
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "doc_url": "<string>",
    "request_id": "<string>",
    "param": "<string>"
  }
}

Transcripts

Get a video transcript

Returns segments, speakers, and entity annotations for a video. Transcript surfaces are premium-only. Access requires a permanent per-video unlock (paid tiers). Cost is always quoted in rows and 15-minute blocks: 75 rows per 15-minute block of video, minimum one block. access states: unlocked (full premium transcript), locked (premium transcript exists — ~5 teaser segments + meta.quote; pass ?unlock=true to debit the quoted rows and receive the full transcript in the same request), premium_pending (a preliminary analysis exists but premium transcription has not run — the payload carries ONLY detected entity-type counts { people, organizations, products, topics } plus the quote; run the premium analysis via POST /v1/transcriptions; unlock=true is ignored in this state), not_transcribed (not in the index — submit via POST /v1/transcriptions). Unlocks are permanent — subsequent reads are free, and an unlock bought before the premium transcript existed makes the later premium generation free. The response meta.revision is an opaque id for the served transcript + approved-correction state; echo it back when submitting corrections.

GET

transcripts

{video_id}

const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};

fetch('https://api.arcmira.com/v1/transcripts/{video_id}', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

{
  "video": {
    "videoId": "<string>",
    "title": "<string>",
    "channelName": "<string>",
    "channelId": "<string>",
    "publishedAt": "<string>",
    "durationSeconds": 123,
    "viewCount": 123
  },
  "segments": [
    {
      "index": 123,
      "start": 123,
      "end": 123,
      "text": "<string>",
      "speaker": 123
    }
  ],
  "speakers": [
    {
      "id": 123,
      "label": "<string>",
      "role": "<string>",
      "confidence": "<string>",
      "voiceRole": "<string>",
      "entity": {
        "id": 123,
        "name": "<string>",
        "slug": "<string>"
      }
    }
  ],
  "annotations": [
    {
      "segmentIndex": 123,
      "charStart": 123,
      "charEnd": 123,
      "entityId": 123,
      "entityType": "<string>",
      "name": "<string>",
      "slug": "<string>"
    }
  ],
  "meta": {
    "diarized": true,
    "locked": true,
    "quote": {
      "quarters": 123,
      "rows": 123
    },
    "revision": "<string>",
    "overLimit": true,
    "devPreview": true,
    "usageLimit": {
      "message": "<string>",
      "ctaLabel": "<string>",
      "ctaHref": "<string>"
    }
  },
  "detected": {
    "people": 123,
    "organizations": 123,
    "products": 123,
    "topics": 123
  },
  "edits": [
    {
      "id": 123,
      "segmentIndex": 123,
      "originalText": "<string>",
      "correctedText": "<string>",
      "status": "<string>",
      "mine": true
    }
  ],
  "speakerIdentifications": [
    {
      "id": 123,
      "speakerId": 123,
      "entityId": 123,
      "entityName": "<string>",
      "status": "<string>"
    }
  ],
  "speakerEdits": [
    {
      "id": 123,
      "seq": 123,
      "editType": "<string>",
      "selection": {
        "startIndex": 123,
        "startChar": 123,
        "endIndex": 123,
        "endChar": 123
      },
      "target": {
        "kind": "<string>",
        "speakerId": 123,
        "label": "<string>",
        "role": "<string>"
      },
      "status": "<string>"
    }
  ],
  "entityTags": [
    {
      "id": 123,
      "seq": 123,
      "segmentIndex": 123,
      "charStart": 123,
      "charEnd": 123,
      "selectedText": "<string>",
      "entity": {
        "id": 123,
        "name": "<string>",
        "slug": "<string>",
        "type": "<string>"
      },
      "status": "<string>"
    }
  ],
  "segmentRewrites": [
    {
      "id": 123,
      "seq": 123,
      "startIndex": 123,
      "endIndex": 123,
      "replacements": [
        {
          "text": "<string>",
          "speaker": 123,
          "start": 123,
          "end": 123
        }
      ],
      "status": "<string>"
    }
  ]
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "doc_url": "<string>",
    "request_id": "<string>",
    "param": "<string>"
  }
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "doc_url": "<string>",
    "request_id": "<string>",
    "param": "<string>"
  }
}

{
  "error": "<string>",
  "quote": {
    "quarters": 123,
    "rows": 123
  }
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "doc_url": "<string>",
    "request_id": "<string>",
    "param": "<string>"
  }
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "doc_url": "<string>",
    "request_id": "<string>",
    "param": "<string>"
  }
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "doc_url": "<string>",
    "request_id": "<string>",
    "param": "<string>"
  }
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "doc_url": "<string>",
    "request_id": "<string>",
    "param": "<string>"
  }
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "doc_url": "<string>",
    "request_id": "<string>",
    "param": "<string>"
  }
}

Authorizations

Authorization

string

header

required

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

Query Parameters

unlock

enum<string>

Explicit purchase action: debits 75 rows per 15-minute block and grants the permanent per-video unlock in the same request. Without it, locked viewers receive only the teaser segments.

Available options:

true

Response

Success

video

object | null

required

Video metadata. Null only when the video is not in the index and no public metadata could be fetched.

Show child attributes

access

enum<string>

required

Access state. Values: unlocked (full premium transcript in this payload), locked (a premium transcript exists; you receive only ~5 teaser segments — pass unlock=true to debit the quoted rows and receive the full transcript), premium_pending (a preliminary analysis exists but the premium transcript has not been generated; payload carries only detected entity-type counts plus the quote — submit POST /v1/transcriptions to generate), not_transcribed (video is not in the index; submit POST /v1/transcriptions), unauthenticated (no authenticated caller; teaser only).

Available options:

unlocked,

locked,

premium_pending,

not_transcribed,

unauthenticated

segments

object[]

required

Transcript segments. Full list when unlocked; first ~5 teaser segments when locked/unauthenticated; empty for premium_pending and not_transcribed.

Show child attributes

speakers

object[]

required

Diarized speakers. Filtered to teaser segments when locked; empty when no diarized transcript exists.

Show child attributes

annotations

object[]

required

Entity annotations as character spans inside segment text. Restricted to teaser segments when locked.

Show child attributes