GET
/
v1
/
transcript
/
id
/
{id}
/
sentences
curl -X GET https://api.verbalisai.com/v1/transcript/id/trans_1234567890/sentences \
  -H "Authorization: Bearer YOUR_API_KEY"
{
  "success": true,
  "data": {
    "transcription_id": "trans_1234567890",
    "total_sentences": 4,
    "total_duration": 12.5,
    "sentences": [
      {
        "id": 1,
        "text": "Hello, welcome to our audio transcription service.",
        "start": 0.0,
        "end": 3.2,
        "confidence": 0.96,
        "words": [
          {
            "word": "Hello",
            "start": 0.0,
            "end": 0.5,
            "confidence": 0.98
          },
          {
            "word": "welcome",
            "start": 0.6,
            "end": 1.1,
            "confidence": 0.97
          }
        ]
      },
      {
        "id": 2,
        "text": "We provide high-quality speech-to-text conversion.",
        "start": 3.3,
        "end": 7.1,
        "confidence": 0.94,
        "words": [
          {
            "word": "We",
            "start": 3.3,
            "end": 3.5,
            "confidence": 0.95
          },
          {
            "word": "provide",
            "start": 3.6,
            "end": 4.1,
            "confidence": 0.93
          }
        ]
      },
      {
        "id": 3,
        "text": "Our API supports multiple languages and formats.",
        "start": 7.2,
        "end": 10.8,
        "confidence": 0.92,
        "words": [
          {
            "word": "Our",
            "start": 7.2,
            "end": 7.4,
            "confidence": 0.94
          }
        ]
      },
      {
        "id": 4,
        "text": "Thank you for using our service.",
        "start": 10.9,
        "end": 12.5,
        "confidence": 0.97,
        "words": [
          {
            "word": "Thank",
            "start": 10.9,
            "end": 11.2,
            "confidence": 0.98
          }
        ]
      }
    ],
    "statistics": {
      "average_confidence": 0.95,
      "words_per_minute": 140,
      "speaking_rate": "normal"
    }
  }
}

Retrieve detailed sentence-level transcription data with timestamps, confidence scores, and additional metadata.

id
string
required

Unique transcription identifier

curl -X GET https://api.verbalisai.com/v1/transcript/id/trans_1234567890/sentences \
  -H "Authorization: Bearer YOUR_API_KEY"
{
  "success": true,
  "data": {
    "transcription_id": "trans_1234567890",
    "total_sentences": 4,
    "total_duration": 12.5,
    "sentences": [
      {
        "id": 1,
        "text": "Hello, welcome to our audio transcription service.",
        "start": 0.0,
        "end": 3.2,
        "confidence": 0.96,
        "words": [
          {
            "word": "Hello",
            "start": 0.0,
            "end": 0.5,
            "confidence": 0.98
          },
          {
            "word": "welcome",
            "start": 0.6,
            "end": 1.1,
            "confidence": 0.97
          }
        ]
      },
      {
        "id": 2,
        "text": "We provide high-quality speech-to-text conversion.",
        "start": 3.3,
        "end": 7.1,
        "confidence": 0.94,
        "words": [
          {
            "word": "We",
            "start": 3.3,
            "end": 3.5,
            "confidence": 0.95
          },
          {
            "word": "provide",
            "start": 3.6,
            "end": 4.1,
            "confidence": 0.93
          }
        ]
      },
      {
        "id": 3,
        "text": "Our API supports multiple languages and formats.",
        "start": 7.2,
        "end": 10.8,
        "confidence": 0.92,
        "words": [
          {
            "word": "Our",
            "start": 7.2,
            "end": 7.4,
            "confidence": 0.94
          }
        ]
      },
      {
        "id": 4,
        "text": "Thank you for using our service.",
        "start": 10.9,
        "end": 12.5,
        "confidence": 0.97,
        "words": [
          {
            "word": "Thank",
            "start": 10.9,
            "end": 11.2,
            "confidence": 0.98
          }
        ]
      }
    ],
    "statistics": {
      "average_confidence": 0.95,
      "words_per_minute": 140,
      "speaking_rate": "normal"
    }
  }
}

Response Fields

transcription_id
string

Unique transcription identifier

total_sentences
integer

Total number of sentences in the transcription

sentences
array
statistics
object

Use Cases

This endpoint is particularly useful for:

  • Subtitle Generation: Create time-coded subtitles for videos
  • Audio Analysis: Analyze speaking patterns and pacing
  • Interactive Transcripts: Build clickable transcript interfaces
  • Quality Assessment: Review confidence scores for accuracy
  • Content Segmentation: Break content into meaningful chunks

Notes

  • Requires authentication (API key)
  • Returns detailed word-level timestamps for precise timing
  • Confidence scores help identify potentially inaccurate segments
  • Speaking rate analysis provides additional audio insights
  • Useful for building interactive transcript experiences